BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Yuan Zhou

Yuan Zhou contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningComputer VisionArtificial Intelligencephysics.app-phphysics.opticscond-mat.mes-hallmath.OCquant-phComputer Science and Game TheoryData Structures and Algorithmseess.IVmath.APProgramming LanguagesSoftware EngineeringComputation and LanguageCryptography and SecurityDistributed, Parallel, and Cluster ComputingLogic in Computer ScienceNetworking and Internet Architecture

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
49works
0followers
19topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

49 published item(s)

preprint2026arXiv

Beyond the Last Layer: Multi-Layer Representation Fusion for Visual Tokenization

Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quality. However, existing methods universally extract features from only the last encoder layer, discarding the rich hierarchical information distributed across intermediate layers. We show that low-level visual details survive in the last layer merely as attenuated residuals after multiple layers of semantic abstraction, and that explicitly fusing multi-layer features can substantially recover this lost information. We propose DRoRAE (Depth-Routed Representation AutoEncoder), a lightweight fusion module that adaptively aggregates all encoder layers via energy-constrained routing and incremental correction, producing an enriched latent compatible with a frozen pretrained decoder. A three-phase decoupled training strategy first learns the fusion under the implicit distributional constraint of the frozen decoder, then fine-tunes the decoder to fully exploit the enriched representation. On ImageNet-256, DRoRAE reduces rFID from 0.57 to 0.29 and improves generation FID from 1.74 to 1.65 (with AutoGuidance), with gains also transferring to text-to-image synthesis. Furthermore, we uncover a log-linear scaling law ($R^2{=}0.86$) between fusion capacity and reconstruction quality, identifying \textit{representation richness} as a new, predictably scalable dimension for visual tokenizers analogous to vocabulary size in NLP.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Drivora: A Unified and Extensible Infrastructure for Search-based Autonomous Driving Testing

Search-based testing is critical for evaluating the safety and reliability of autonomous driving systems (ADSs). However, existing approaches are often built on heterogeneous frameworks (e.g., distinct scenario spaces, simulators, and ADSs), which require considerable effort to reuse and adapt across different settings. To address these challenges, we present Drivora, a unified and extensible infrastructure for search-based ADS testing built on the widely used CARLA simulator. Drivora introduces a unified scenario definition, OpenScenario, that specifies scenarios using low-level, actionable parameters to ensure compatibility with existing methods while supporting extensibility to new testing designs (e.g., multi-autonomous-vehicle testing). On top of this, Drivora decouples the testing engine, scenario execution, and ADS integration. The testing engine leverages evolutionary computation to explore new scenarios and supports flexible customization of core components. The scenario execution can run arbitrary scenarios using a parallel execution mechanism that maximizes hardware utilization for large-scale batch simulation. For ADS integration, Drivora provides access to 12 ADSs through a unified interface, streamlining configuration and simplifying the incorporation of new ADSs. Our tools are publicly available at https://github.com/MingfeiCheng/Drivora.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Learning in Position-Aware Multinomial Logit Bandits: From Multiplicative to General Position Effects

We study the dynamic joint assortment selection and positioning problem, where the attraction of each product depends on both its intrinsic appeal and its display position under a Multinomial Logit (MNL) choice framework. Our study ranges from the multiplicative position effects model, in which each product's attraction is scaled by a position-specific factor, to a general position effects model assigning independent attraction parameters to every product--position pair to capture heterogeneous synergies. For both models, we design round-based learning algorithms that update decisions after every single feedback, and establish the first regret-optimal characterization. Besides, our round-based algorithms provide the prompt operations needed by modern platforms. For the multiplicative model, we develop a cross-position pairwise maximum likelihood estimator with a clipping mechanism, and prove that our algorithm P2MLE-UCB attains a regret of $\tilde{O}(\sqrt{NT})$, matching the lower bound and closing the $\sqrt{K}$ gap left by prior epoch-based analyses. For the general model, we establish a minimax lower bound and propose GP2-UCB with a matching upper bound. Moreover, we design an efficient subroutine for the per-round joint assortment and positioning optimization based on Dinkelbach's method and maximum-weight bipartite matching. Numerical experiments on synthetic data and the Expedia dataset show that our algorithms consistently outperform state-of-the-art benchmarks.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Perturbed Proximal Gradient ADMM for Nonconvex Composite Optimization

This paper proposes a Perturbed Proximal Gradient ADMM (PPG-ADMM) framework for solving general nonconvex composite optimization problems, where the objective function consists of a smooth nonconvex term and a nonsmooth weakly convex term for both primal variables. Unlike existing ADMM-based methods which necessitate the function associated with the last updated primal variable to be smooth, the proposed PPG-ADMM removes this restriction by introducing a perturbation mechanism, which also helps reduce oscillations in the primal-dual updates, thereby improving convergence stability. By employing a linearization technique for the smooth term and the proximal operator for the nonsmooth and weakly convex term, the subproblems have closed-form solutions, significantly reducing computational complexity. The convergence is established through a technically constructed Lyapunov function, which guarantees sufficient descent and has a well-defined lower bound. With properly chosen parameters, PPG-ADMM converges to an $ε$-approximate stationary point at a sublinear convergence rate of $\mathcal{O}(1/\sqrt{K})$. Furthermore, by appropriately tuning the perturbation parameter $β$, it achieves an $ε$-stationary point, providing stronger optimality guarantees. We further apply PPG-ADMM to two practical distributed nonconvex composite optimization problems, i.e., the distributed partial consensus problem and the resource allocation problem. The algorithm operates in a fully decentralized manner without a central coordinating node. Finally, numerical experiments validate the effectiveness of PPG-ADMM, demonstrating its improved convergence performance.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Rewarding Beliefs, Not Actions: Consistency-Guided Credit Assignment for Long-Horizon Agents

Reinforcement learning from verifiable rewards (RLVR) is a promising paradigm for improving large language model (LLM) agents on long-horizon interactive tasks. However, in partially observable environments, incomplete observations cause agent beliefs to drift over time, while delayed rewards obscure the causal impact of intermediate decisions, exacerbating temporal credit assignment challenges. To address this, we propose ReBel (Reward Belief), a process-level reinforcement learning algorithm that explicitly models structured belief states to summarize interaction history and guide subsequent policy learning. ReBel introduces belief-consistency supervision, converting discrepancies between predicted beliefs and observed feedback into dense self-supervised signals without requiring external step-wise annotations or verifiers. It also employs belief-aware grouping to compare trajectories under similar belief states, yielding more robust and lower-variance advantage estimates. We evaluate ReBel on challenging long-horizon benchmarks, including ALFWorld and WebShop. ReBel improves task success by up to $20.4$ percentage points over the episode-level baseline GRPO and increases sample efficiency by $2.1\times$. These results suggest that belief-aware self-supervision is a promising direction for reliable long-horizon decision-making under partial observability. Code is available at: https://github.com/Fateyetian/Rebel.git.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models

Recent video diffusion models (VDMs) synthesize visually convincing clips, yet still drop entities, mis-bind attributes, and weaken the interactions specified in the prompt. Representation-alignment objectives such as VideoREPA and MoAlign improve fine-grained text following by distilling spatio-temporal token relations from a frozen visual foundation model, but their pairwise supervision budget is allocated by visual or motion cues rather than by how relevant each pair is to the prompt. We present SARA, Semantically Adaptive Relational Alignment, which keeps token-relation distillation (TRD) on a frozen VFM target and adds a text-conditioned saliency that decides which token pairs carry supervision. A lightweight Stage 1 aligner is trained with per-entity SAM 3.1 mask supervision and an InfoNCE regulariser, and its continuous saliency is fused into TRD through a pair-routing operator that assigns each token pair a weight whenever either of its two endpoints is salient, thereby routing supervision toward subject-subject and subject-background pairs and away from background-background ones. In the Wan2.2 continual-training setting, SARA improves both text alignment and motion quality over SFT, VideoREPA, and MoAlign on a 13-dimension VLM rubric, on the public VBench benchmarks, and in a blind user study.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Video Generation Models Are Good Latent Reward Models

Reward feedback learning (ReFL) has proven effective for aligning image generation with human preferences. However, its extension to video generation faces significant challenges. Existing video reward models rely on vision-language models designed for pixel-space inputs, confining ReFL optimization to near-complete denoising steps after computationally expensive VAE decoding. This pixel-space approach incurs substantial memory overhead and increased training time, and its late-stage optimization lacks early-stage supervision, refining only visual quality rather than fundamental motion dynamics and structural coherence. In this work, we show that pre-trained video generation models are naturally suited for reward modeling in the noisy latent space, as they are explicitly designed to process noisy latent representations at arbitrary timesteps and inherently preserve temporal information through their sequential modeling capabilities. Accordingly, we propose Process Reward Feedback Learning~(PRFL), a framework that conducts preference optimization entirely in latent space, enabling efficient gradient backpropagation throughout the full denoising chain without VAE decoding. Extensive experiments demonstrate that PRFL significantly improves alignment with human preferences, while achieving substantial reductions in memory consumption and training time compared to RGB ReFL.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A global second order Sobolev regularity for $p$-Laplacian type equations with variable coefficients in bounded domains

Let $Ω\subset R^n$ be a bounded convex domain with $n\ge2$. Suppose that $A$ is uniformly elliptic and belongs to $W^{1,n}$ when $n\ge 3$ or $W^{1,q}$ for some $q>2$ when $n=2$. For $1<p<\infty$, we build up a global second order regularity estimate $$\|D[|Du|^{p-2} Du]\|_{L^2(Ω)}+\|D[ |\sqrt{A}Du|^{p-2} A Du]\|_{L^2(Ω)} \le C \|f\|_{L^2(Ω)} $$ for inhomogeneous $p$-Laplace type equation \begin{equation} -\mathrm{div}\big(\langle A Du,Du\rangle ^{\frac{p-2}2} A Du\big)=f \quad\rm{in }\ Ω\mbox{ with Dirichlet/Neumann $0$-boundary.} \end{equation} Similar result was also built up for certain bounded Lipschitz domain whose boundary is weakly second order differentiable and satisfies some smallness assumptions.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

AACC: Asymmetric Actor-Critic in Contextual Reinforcement Learning

Reinforcement Learning (RL) techniques have drawn great attention in many challenging tasks, but their performance deteriorates dramatically when applied to real-world problems. Various methods, such as domain randomization, have been proposed to deal with such situations by training agents under different environmental setups, and therefore they can be generalized to different environments during deployment. However, they usually do not incorporate the underlying environmental factor information that the agents interact with properly and thus can be overly conservative when facing changes in the surroundings. In this paper, we first formalize the task of adapting to changing environmental dynamics in RL as a generalization problem using Contextual Markov Decision Processes (CMDPs). We then propose the Asymmetric Actor-Critic in Contextual RL (AACC) as an end-to-end actor-critic method to deal with such generalization tasks. We demonstrate the essential improvements in the performance of AACC over existing baselines experimentally in a range of simulated environments.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Adaptive Double-Exploration Tradeoff for Outlier Detection

We study a variant of the thresholding bandit problem (TBP) in the context of outlier detection, where the objective is to identify the outliers whose rewards are above a threshold. Distinct from the traditional TBP, the threshold is defined as a function of the rewards of all the arms, which is motivated by the criterion for identifying outliers. The learner needs to explore the rewards of the arms as well as the threshold. We refer to this problem as &#34;double exploration for outlier detection&#34;. We construct an adaptively updated confidence interval for the threshold, based on the estimated value of the threshold in the previous rounds. Furthermore, by automatically trading off exploring the individual arms and exploring the outlier threshold, we provide an efficient algorithm in terms of the sample complexity. Experimental results on both synthetic datasets and real-world datasets demonstrate the efficiency of our algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Automatic Map Generation for Autonomous Driving System Testing

High-definition (HD) maps are essential in testing autonomous driving systems (ADSs). HD maps essentially determine the potential diversity of the testing scenarios. However, the current HD maps suffer from two main limitations: lack of junction diversity in the publicly available HD maps and cost-consuming to build a new HD map. Hence, in this paper, we propose, FEAT2MAP, to automatically generate concise HD maps with scenario diversity guarantees. FEAT2MAP focuses on junctions as they significantly influence scenario diversity, especially in urban road networks. FEAT2MAP first defines a set of features to characterize junctions. Then, FEAT2MAP extracts and samples concrete junction features from a list of input HD maps or user-defined requirements. Each junction feature generates a junction. Finally, FEAT2MAP builds a map by connecting the junctions in a grid layout. To demonstrate the effectiveness of FEAT2MAP, we conduct experiments with the public HD maps from SVL and the open-source ADS Apollo. The results show that FEAT2MAP can (1) generate new maps of reduced size while maintaining scenario diversity in terms of the code coverage and motion states of the ADS under test, and (2) generate new maps of increased scenario diversity by merging intersection features from multiple maps or taking user inputs.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dynamic Car Dispatching and Pricing: Revenue and Fairness for Ridesharing Platforms

A major challenge for ridesharing platforms is to guarantee profit and fairness simultaneously, especially in the presence of misaligned incentives of drivers and riders. We focus on the dispatching-pricing problem to maximize the total revenue while keeping both drivers and riders satisfied. We study the computational complexity of the problem, provide a novel two-phased pricing solution with revenue and fairness guarantees, extend it to stochastic settings and develop a dynamic (a.k.a., learning-while-doing) algorithm that actively collects data to learn the demand distribution during the scheduling process. We also conduct extensive experiments to demonstrate the effectiveness of our algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Generating Adjacency Matrix for Video Relocalization

In this paper, we continue our work on video relocalization task. Based on using graph convolution to extract intra-video and inter-video frame features, we improve the method by using similarity-metric based graph convolution, whose weighted adjacency matrix is achieved by calculating similarity metric between features of any two different time steps in the graph. Experiments on ActivityNet v1.2 and Thumos14 dataset show the effectiveness of this improvement, and it outperforms the state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Graph Neural Network for Video Relocalization

In this paper, we focus on video relocalization task, which uses a query video clip as input to retrieve a semantic relative video clip in another untrimmed long video. we find that in video relocalization datasets, there exists a phenomenon showing that there does not exist consistent relationship between feature similarity by frame and feature similarity by video, which affects the feature fusion among frames. However, existing video relocalization methods do not fully consider it. Taking this phenomenon into account, in this article, we treat video features as a graph by concatenating the query video feature and proposal video feature along time dimension, where each timestep is treated as a node, each row of the feature matrix is treated as feature of each node. Then, with the power of graph neural networks, we propose a Multi-Graph Feature Fusion Module to fuse the relation feature of this graph. After evaluating our method on ActivityNet v1.2 dataset and Thumos14 dataset, we find that our proposed method outperforms the state of art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Imitation Learning from Observations under Transition Model Disparity

Learning to perform tasks by leveraging a dataset of expert observations, also known as imitation learning from observations (ILO), is an important paradigm for learning skills without access to the expert reward function or the expert actions. We consider ILO in the setting where the expert and the learner agents operate in different environments, with the source of the discrepancy being the transition dynamics model. Recent methods for scalable ILO utilize adversarial learning to match the state-transition distributions of the expert and the learner, an approach that becomes challenging when the dynamics are dissimilar. In this work, we propose an algorithm that trains an intermediary policy in the learner environment and uses it as a surrogate expert for the learner. The intermediary policy is learned such that the state transitions generated by it are close to the state transitions in the expert dataset. To derive a practical and scalable algorithm, we employ concepts from prior work on estimating the support of a probability distribution. Experiments using MuJoCo locomotion tasks highlight that our method compares favorably to the baselines for ILO with transition dynamics mismatch.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Interior Hölder regularity for stable solutions to semilinear elliptic equations up to dimension 5

Let $2\le n\le 5$. We establish an apriori interior Hölder regularity of $C^2$-stable solutions to the semilinear equation $-Δu=f(u)$ in any domain of $R^n$ for any nonlinearity $f\in C^{0,1}(R) $.If $f $ is nondecreasing and convex in addition,we obtain an interior Hölder regularity, and hence the local boundedness, of $W^{1,2}(Ω)$-stable solutions by locally approximating them via $C^2(Ω)$-stable solutions. In particular, we do not require any lower bound on $f$.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Long-Term Reward Redistribution via Randomized Return Decomposition

Many practical applications of reinforcement learning require agents to learn from sparse and delayed rewards. It challenges the ability of agents to attribute their actions to future outcomes. In this paper, we consider the problem formulation of episodic reinforcement learning with trajectory feedback. It refers to an extreme delay of reward signals, in which the agent can only obtain one reward signal at the end of each trajectory. A popular paradigm for this problem setting is learning with a designed auxiliary dense reward function, namely proxy reward, instead of sparse environmental signals. Based on this framework, this paper proposes a novel reward redistribution algorithm, randomized return decomposition (RRD), to learn a proxy reward function for episodic reinforcement learning. We establish a surrogate problem by Monte-Carlo sampling that scales up least-squares-based reward redistribution to long-horizon problems. We analyze our surrogate loss function by connection with existing methods in the literature, which illustrates the algorithmic properties of our approach. In experiments, we extensively evaluate our proposed method on a variety of benchmark tasks with episodic rewards and demonstrate substantial improvement over baseline algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Monolithically integrated active passive waveguide array fabricated on thin film lithium niobate using a single continuous photolithography process

We demonstrate a robust low-loss optical interface by tiling passive (i.e., without doping of active ions) thin film lithium niobate (TFLN) and active (i.e., doped with rare earth ions) TFLN substrates for monolithic integration of passive/active lithium niobate photonics. The tiled substrates composed of both active and passive areas allow to pattern the mask of the integrated active passive photonic device at once using a single continuous photolithography process. The interface loss of tiled substrate is measured as low as 0.26 dB. Thanks to the stability provided by this approach, a four-channel waveguide amplifier is realized in a straightforward manner, which shows a net gain of ~5 dB at 1550-nm wavelength and that of ~8 dB at 1530-nm wavelength for each channel. The robust low-loss optical interface for passive/active photonic integration will facilitate large-scale high performance photonic devices which require on-chip light sources and amplifiers.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Monolithically integrated waveguide-coupled single-frequency microlaser on erbium-doped thin film lithium niobate

We overcome the difficulty in realizing a monolithic waveguide-coupled microring laser integrated on erbium-doped thin film lithium niobate (Er: TFLN) using photolithography assisted chemo-mechanical etching (PLACE) technique. We demonstrate an integrated single-frequency microring laser operating around 1531 nm wavelength. The PLACE technique, enabling integrated Er: TFLN photonics with low propagation loss, can thus be used to realize low cost mass production of monolithic on-chip microlasers with applications ranging from optical communication and photonic integrated circuit (PIC) to precision metrology and large-scale sensing.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On-chip integrated Yb3+-doped waveguide amplifiers on thin film lithium niobate

We report the fabrication and optical characterization of Yb3+-doped waveguide amplifiers (YDWA) on the thin film lithium niobate fabricated by photolithography assisted chemo-mechanical etching. The fabricated Yb3+-doped lithium niobate waveguides demonstrates low propagation loss of 0.13 dB/cm at 1030 nm and 0.1 dB/cm at 1060 nm. The internal net gain of 5 dB at 1030 nm and 8 dB at 1060 nm are measured on a 4.0 cm long waveguide pumped by 976nm laser diodes, indicating the gain per unit length of 1.25 dB/cm at 1030 nm and 2 dB/cm at 1060 nm, respectively. The integrated Yb3+-doped lithium niobate waveguide amplifiers will benefit the development of a powerful gain platform and are expected to contribute to the high-density integration of thin film lithium niobate based photonic chip.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Physical Backdoor Attacks to Lane Detection Systems in Autonomous Driving

Modern autonomous vehicles adopt state-of-the-art DNN models to interpret the sensor data and perceive the environment. However, DNN models are vulnerable to different types of adversarial attacks, which pose significant risks to the security and safety of the vehicles and passengers. One prominent threat is the backdoor attack, where the adversary can compromise the DNN model by poisoning the training samples. Although lots of effort has been devoted to the investigation of the backdoor attack to conventional computer vision tasks, its practicality and applicability to the autonomous driving scenario is rarely explored, especially in the physical world. In this paper, we target the lane detection system, which is an indispensable module for many autonomous driving tasks, e.g., navigation, lane switching. We design and realize the first physical backdoor attacks to such system. Our attacks are comprehensively effective against different types of lane detection algorithms. Specifically, we introduce two attack methodologies (poison-annotation and clean-annotation) to generate poisoned samples. With those samples, the trained lane detection model will be infected with the backdoor, and can be activated by common objects (e.g., traffic cones) to make wrong detections, leading the vehicle to drive off the road or onto the opposite lane. Extensive evaluations on public datasets and physical autonomous vehicles demonstrate that our backdoor attacks are effective, stealthy and robust against various defense solutions. Our codes and experimental videos can be found in https://sites.google.com/view/lane-detection-attack/lda.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Real-time Semantic Segmentation via Spatial-detail Guided Context Propagation

Nowadays, vision-based computing tasks play an important role in various real-world applications. However, many vision computing tasks, e.g. semantic segmentation, are usually computationally expensive, posing a challenge to the computing systems that are resource-constrained but require fast response speed. Therefore, it is valuable to develop accurate and real-time vision processing models that only require limited computational resources. To this end, we propose the Spatial-detail Guided Context Propagation Network (SGCPNet) for achieving real-time semantic segmentation. In SGCPNet, we propose the strategy of spatial-detail guided context propagation. It uses the spatial details of shallow layers to guide the propagation of the low-resolution global contexts, in which the lost spatial information can be effectively reconstructed. In this way, the need for maintaining high-resolution features along the network is freed, therefore largely improving the model efficiency. On the other hand, due to the effective reconstruction of spatial details, the segmentation accuracy can be still preserved. In the experiments, we validate the effectiveness and efficiency of the proposed SGCPNet model. On the Citysacpes dataset, for example, our SGCPNet achieves 69.5% mIoU segmentation accuracy, while its speed reaches 178.5 FPS on 768x1536 images on a GeForce GTX 1080 Ti GPU card. In addition, SGCPNet is very lightweight and only contains 0.61 M parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentation

Automated segmentation in medical image analysis is a challenging task that requires a large amount of manually labeled data. However, most existing learning-based approaches usually suffer from limited manually annotated medical data, which poses a major practical problem for accurate and robust medical image segmentation. In addition, most existing semi-supervised approaches are usually not robust compared with the supervised counterparts, and also lack explicit modeling of geometric structure and semantic information, both of which limit the segmentation accuracy. In this work, we present SimCVD, a simple contrastive distillation framework that significantly advances state-of-the-art voxel-wise representation learning. We first describe an unsupervised training strategy, which takes two views of an input volume and predicts their signed distance maps of object boundaries in a contrastive objective, with only two independent dropout as mask. This simple approach works surprisingly well, performing on the same level as previous fully supervised methods with much less labeled data. We hypothesize that dropout can be viewed as a minimal form of data augmentation and makes the network robust to representation collapse. Then, we propose to perform structural distillation by distilling pair-wise similarities. We evaluate SimCVD on two popular datasets: the Left Atrial Segmentation Challenge (LA) and the NIH pancreas CT dataset. The results on the LA dataset demonstrate that, in two types of labeled ratios (i.e., 20% and 10%), SimCVD achieves an average Dice score of 90.85% and 89.03% respectively, a 0.91% and 2.22% improvement compared to previous best results. Our method can be trained in an end-to-end fashion, showing the promise of utilizing SimCVD as a general framework for downstream tasks, such as medical image synthesis, enhancement, and registration.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records

With the successful adoption of machine learning on electronic health records (EHRs), numerous computational models have been deployed to address a variety of clinical problems. However, due to the heterogeneity of EHRs, models trained on different patient groups suffer from poor generalizability. How to mitigate domain shifts between the source patient group where the model is built upon and the target one where the model will be deployed becomes a critical issue. In this paper, we propose a data augmentation method to facilitate domain adaptation, which leverages knowledge from the source patient group when training model on the target one. Specifically, adversarially generated samples are used during domain adaptation to fill the generalization gap between the two patient groups. The proposed method is evaluated by a case study on different predictive modeling tasks on MIMIC-III EHR dataset. Results confirm the effectiveness of our method and the generality on different tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Dynamic Assortment Selection under the Nested Logit Models

We study a stylized dynamic assortment planning problem during a selling season of finite length $T$. At each time period, the seller offers an arriving customer an assortment of substitutable products and the customer makes the purchase among offered products according to a discrete choice model. The goal of the seller is to maximize the expected revenue, or equivalently, to minimize the worst-case expected regret. One key challenge is that utilities of products are unknown to the seller and need to be learned. Although the dynamic assortment planning problem has received increasing attention in revenue management, most existing work is based on the multinomial logit choice models (MNL). In this paper, we study the problem of dynamic assortment planning under a more general choice model -- the nested logit model, which models hierarchical choice behavior and is ``the most widely used member of the GEV (generalized extreme value) family&#39;&#39;. By leveraging the revenue-ordered structure of the optimal assortment within each nest, we develop a novel upper confidence bound (UCB) policy with an aggregated estimation scheme. Our policy simultaneously learns customers&#39; choice behavior and makes dynamic decisions on assortments based on the current knowledge. It achieves the accumulated regret at the order of $\tilde{O}(\sqrt{MNT})$, where $M$ is the number of nests and $N$ is the number of products in each nest. We further provide a lower bound result of $Ω(\sqrt{MT})$, which shows the near optimality of the upper bound when $T$ is much larger than $M$ and $N$. When the number of items per nest $N$ is large, we further provide a discretization heuristic for better performance of our algorithm. Numerical results are presented to demonstrate the empirical performance of our proposed algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

On-chip integrated waveguide amplifiers on Erbium-doped thin film lithium niobate on insulator

We demonstrate on-chip light amplification with integrated optical waveguide fabricated on erbium-doped thin film lithium niobate on insulator (TFLNOI) using the photolithography assisted chemo-mechanical etching (PLACE) technique. A maximum internal net gain of 18 dB in the small-signal-gain regime is measured at the peak emission wavelength of 1530 nm for a waveguide length of 3.6 cm, indicating a differential gain per unit length of 5 dB/cm. This work paves the way to the monolithic integration of diverse active and passive photonic components on the TFLNOI platform.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Probabilistic Programs with Stochastic Conditioning

We tackle the problem of conditioning probabilistic programs on distributions of observable variables. Probabilistic programs are usually conditioned on samples from the joint data distribution, which we refer to as deterministic conditioning. However, in many real-life scenarios, the observations are given as marginal distributions, summary statistics, or samplers. Conventional probabilistic programming systems lack adequate means for modeling and inference in such scenarios. We propose a generalization of deterministic conditioning to stochastic conditioning, that is, conditioning on the marginal distribution of a variable taking a particular form. To this end, we first define the formal notion of stochastic conditioning and discuss its key properties. We then show how to perform inference in the presence of stochastic conditioning. We demonstrate potential usage of stochastic conditioning on several case studies which involve various kinds of stochastic conditioning and are difficult to solve otherwise. Although we present stochastic conditioning in the context of probabilistic programming, our formalization is general and applicable to other settings.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Scaling Up Hardware Accelerator Verification using A-QED with Functional Decomposition

Hardware accelerators (HAs) are essential building blocks for fast and energy-efficient computing systems. Accelerator Quick Error Detection (A-QED) is a recent formal technique which uses Bounded Model Checking for pre-silicon verification of HAs. A-QED checks an HA for self-consistency, i.e., whether identical inputs within a sequence of operations always produce the same output. Under modest assumptions, A-QED is both sound and complete. However, as is well-known, large design sizes significantly limit the scalability of formal verification, including A-QED. We overcome this scalability challenge through a new decomposition technique for A-QED, called A-QED with Decomposition (A-QED$^2$). A-QED$^2$ systematically decomposes an HA into smaller, functional sub-modules, called sub-accelerators, which are then verified independently using A-QED. We prove completeness of A-QED$^2$; in particular, if the full HA under verification contains a bug, then A-QED$^2$ ensures detection of that bug during A-QED verification of the corresponding sub-accelerators. Results on over 100 (buggy) versions of a wide variety of HAs with millions of logic gates demonstrate the effectiveness and practicality of A-QED$^2$.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Tight Regret Bounds for Infinite-armed Linear Contextual Bandits

Linear contextual bandit is an important class of sequential decision making problems with a wide range of applications to recommender systems, online advertising, healthcare, and many other machine learning related tasks. While there is a lot of prior research, tight regret bounds of linear contextual bandit with infinite action sets remain open. In this paper, we address this open problem by considering the linear contextual bandit with (changing) infinite action sets. We prove a regret upper bound on the order of $O(\sqrt{d^2T\log T})\times \text{poly}(\log\log T)$ where $d$ is the domain dimension and $T$ is the time horizon. Our upper bound matches the previous lower bound of $Ω(\sqrt{d^2 T\log T})$ in [Li et al., 2019] up to iterated logarithmic terms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

$\sqrt{n}$-Regret for Learning in Markov Decision Processes with Function Approximation and Low Bellman Rank

In this paper, we consider the problem of online learning of Markov decision processes (MDPs) with very large state spaces. Under the assumptions of realizable function approximation and low Bellman ranks, we develop an online learning algorithm that learns the optimal value function while at the same time achieving very low cumulative regret during the learning process. Our learning algorithm, Adaptive Value-function Elimination (AVE), is inspired by the policy elimination algorithm proposed in (Jiang et al., 2017), known as OLIVE. One of our key technical contributions in AVE is to formulate the elimination steps in OLIVE as contextual bandit problems. This technique enables us to apply the active elimination and expert weighting methods from (Dudik et al., 2011), instead of the random action exploration scheme used in the original OLIVE algorithm, for more efficient exploration and better control of the regret incurred in each policy elimination step. To the best of our knowledge, this is the first $\sqrt{n}$-regret result for reinforcement learning in stochastic MDPs with general value function approximation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition

We study the reinforcement learning problem in the setting of finite-horizon episodic Markov Decision Processes (MDPs) with $S$ states, $A$ actions, and episode length $H$. We propose a model-free algorithm UCB-Advantage and prove that it achieves $\tilde{O}(\sqrt{H^2SAT})$ regret where $T = KH$ and $K$ is the number of episodes to play. Our regret bound improves upon the results of [Jin et al., 2018] and matches the best known model-based algorithms as well as the information theoretic lower bound up to logarithmic factors. We also show that UCB-Advantage achieves low local switching cost and applies to concurrent reinforcement learning, improving upon the recent results of [Bai et al., 2019].

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Anypath Routing Protocol Design via Q-Learning for Underwater Sensor Networks

As a promising technology in the Internet of Underwater Things, underwater sensor networks have drawn a widespread attention from both academia and industry. However, designing a routing protocol for underwater sensor networks is a great challenge due to high energy consumption and large latency in the underwater environment. This paper proposes a Q-learning-based localization-free anypath routing (QLFR) protocol to prolong the lifetime as well as reduce the end-to-end delay for underwater sensor networks. Aiming at optimal routing policies, the Q-value is calculated by jointly considering the residual energy and depth information of sensor nodes throughout the routing process. More specifically, we define two reward functions (i.e., depth-related and energy-related rewards) for Q-learning with the objective of reducing latency and extending network lifetime. In addition, a new holding time mechanism for packet forwarding is designed according to the priority of forwarding candidate nodes. Furthermore, a mathematical analysis is presented to analyze the performance of the proposed routing protocol. Extensive simulation results demonstrate the superiority performance of the proposed routing protocol in terms of the end-to-end delay and the network lifetime.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Collaborative Top Distribution Identifications with Limited Interaction

We consider the following problem in this paper: given a set of $n$ distributions, find the top-$m$ ones with the largest means. This problem is also called {\em top-$m$ arm identifications} in the literature of reinforcement learning, and has numerous applications. We study the problem in the collaborative learning model where we have multiple agents who can draw samples from the $n$ distributions in parallel. Our goal is to characterize the tradeoffs between the running time of learning process and the number of rounds of interaction between agents, which is very expensive in various scenarios. We give optimal time-round tradeoffs, as well as demonstrate complexity separations between top-$1$ arm identification and top-$m$ arm identifications for general $m$ and between fixed-time and fixed-confidence variants. As a byproduct, we also give an algorithm for selecting the distribution with the $m$-th largest mean in the collaborative learning model.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Divide, Conquer, and Combine: a New Inference Strategy for Probabilistic Programs with Stochastic Support

Universal probabilistic programming systems (PPSs) provide a powerful framework for specifying rich probabilistic models. They further attempt to automate the process of drawing inferences from these models, but doing this successfully is severely hampered by the wide range of non--standard models they can express. As a result, although one can specify complex models in a universal PPS, the provided inference engines often fall far short of what is required. In particular, we show that they produce surprisingly unsatisfactory performance for models where the support varies between executions, often doing no better than importance sampling from the prior. To address this, we introduce a new inference framework: Divide, Conquer, and Combine, which remains efficient for such models, and show how it can be implemented as an automated and generic PPS inference engine. We empirically demonstrate substantial performance improvements over existing approaches on three examples.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Domain Adaptive Adversarial Learning Based on Physics Model Feedback for Underwater Image Enhancement

Owing to refraction, absorption, and scattering of light by suspended particles in water, raw underwater images suffer from low contrast, blurred details, and color distortion. These characteristics can significantly interfere with the visibility of underwater images and the result of visual tasks, such as segmentation and tracking. To address this problem, we propose a new robust adversarial learning framework via physics model based feedback control and domain adaptation mechanism for enhancing underwater images to get realistic results. A new method for simulating underwater-like training dataset from RGB-D data by underwater image formation model is proposed. Upon the synthetic dataset, a novel enhancement framework, which introduces a domain adaptive mechanism as well as a physics model constraint feedback control, is trained to enhance the underwater scenes. Final enhanced results on synthetic and real underwater images demonstrate the superiority of the proposed method, which outperforms nondeep and deep learning methods in both qualitative and quantitative evaluations. Furthermore, we perform an ablation study to show the contributions of each component we proposed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Dual-reference Age Synthesis

Age synthesis methods typically take a single image as input and use a specific number to control the age of the generated image. In this paper, we propose a novel framework taking two images as inputs, named dual-reference age synthesis (DRAS), which approaches the task differently; instead of using &#34;hard&#34; age information, i.e. a fixed number, our model determines the target age in a &#34;soft&#34; way, by employing a second reference image. Specifically, the proposed framework consists of an identity agent, an age agent and a generative adversarial network. It takes two images as input - an identity reference and an age reference - and outputs a new image that shares corresponding features with each. Experimental results on two benchmark datasets (UTKFace and CACD) demonstrate the appealing performance and flexibility of the proposed framework.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Efficient Competitive Self-Play Policy Optimization

Reinforcement learning from self-play has recently reported many successes. Self-play, where the agents compete with themselves, is often used to generate training data for iterative policy improvement. In previous work, heuristic rules are designed to choose an opponent for the current learner. Typical rules include choosing the latest agent, the best agent, or a random historical agent. However, these rules may be inefficient in practice and sometimes do not guarantee convergence even in the simplest matrix games. In this paper, we propose a new algorithmic framework for competitive self-play reinforcement learning in two-player zero-sum games. We recognize the fact that the Nash equilibrium coincides with the saddle point of the stochastic payoff function, which motivates us to borrow ideas from classical saddle point optimization literature. Our method trains several agents simultaneously, and intelligently takes each other as opponent based on simple adversarial rules derived from a principled perturbation-based saddle optimization method. We prove theoretically that our algorithm converges to an approximate equilibrium with high probability in convex-concave games under standard assumptions. Beyond the theory, we further show the empirical superiority of our method over baseline methods relying on the aforementioned opponent-selection heuristics in matrix games, grid-world soccer, Gomoku, and simulated robot sumo, with neural net policy function approximators.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Equivariant Perturbation in Gomory and Johnson&#39;s Infinite Group Problem. VII. Inverse semigroup theory, closures, decomposition of perturbations

In this self-contained paper, we present a theory of the piecewise linear minimal valid functions for the 1-row Gomory-Johnson infinite group problem. The non-extreme minimal valid functions are those that admit effective perturbations. We give a precise description of the space of these perturbations as a direct sum of certain finite- and infinite-dimensional subspaces. The infinite-dimensional subspaces have partial symmetries; to describe them, we develop a theory of inverse semigroups of partial bijections, interacting with the functional equations satisfied by the perturbations. Our paper provides the foundation for grid-free algorithms for the Gomory-Johnson model, in particular for testing extremality of piecewise linear functions whose breakpoints are rational numbers with huge denominators.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Furnishing Your Room by What You See: An End-to-End Furniture Set Retrieval Framework with Rich Annotated Benchmark Dataset

Understanding interior scenes has attracted enormous interest in computer vision community. However, few works focus on the understanding of furniture within the scenes and a large-scale dataset is also lacked to advance the field. In this paper, we first fill the gap by presenting DeepFurniture, a richly annotated large indoor scene dataset, including 24k indoor images, 170k furniture instances and 20k unique furniture identities. On the dataset, we introduce a new benchmark, named furniture set retrieval. Given an indoor photo as input, the task requires to detect all the furniture instances and search a matched set of furniture identities. To address this challenging task, we propose a feature and context embedding based framework. It contains 3 major contributions: (1) An improved Mask-RCNN model with an additional mask-based classifier is introduced for better utilizing the mask information to relieve the occlusion problems in furniture detection context. (2) A multi-task style Siamese network is proposed to train the feature embedding model for retrieval, which is composed of a classification subnet supervised by self-clustered pseudo attributes and a verification subnet to estimate whether the input pair is matched. (3) In order to model the relationship of the furniture entities in an interior design, a context embedding model is employed to re-rank the retrieval results. Extensive experiments demonstrate the effectiveness of each module and the overall system.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Giant anisotropy of spin relaxation and spin-valley mixing in a silicon quantum dot

In silicon quantum dots (QDs), at a certain magnetic field commonly referred to as the &#34;hot spot&#34;, the electron spin relaxation rate (T_1^(-1)) can be drastically enhanced due to strong spin-valley mixing. Here, we experimentally find that with a valley splitting of 78.2 ${\pm}$ 1.6 $μ$eV, this hot spot in spin relaxation can be suppressed by more than 2 orders of magnitude when the in-plane magnetic field is oriented at an optimal angle, about 9° from the [100] sample plane. This directional anisotropy exhibits a sinusoidal modulation with a 180° periodicity. We explain the magnitude and phase of this modulation using a model that accounts for both spin-valley mixing and intravalley spin-orbit mixing. The generality of this phenomenon is also confirmed by tuning the electric field and the valley splitting up to 268.2 ${\pm}$ 0.7 $μ$eV.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Improving mobility of silicon metal-oxide-semiconductor devices for quantum dots by high vacuum activation annealing

To improve mobility of fabricated silicon metal-oxide-semiconductor (MOS) quantum devices, forming gas annealing is a common method used to mitigate the effects of disorder at the Si/SiO2 interface. However, the importance of activation annealing is usually ignored. Here, we show that a high vacuum environment for implantation activation is beneficial for improving mobility compared to nitrogen atmosphere. Low-temperature transport measurements of Hall bars show that peak mobility can be improved by a factor of two, reaching 1.5 m^2/(Vs) using high vacuum annealing during implantation activation. Moreover, the charge stability diagram of a single quantum dot is mapped, with no visible disturbance caused by disorder, suggesting possibility of fabricating high-quality quantum dots on commercial wafers. Our results may provide valuable insights into device optimization in silicon-based quantum computing.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-IF : An Approach to Anomaly Detection in Self-Driving Systems

Autonomous driving vehicles (ADVs) are implemented with rich software functions and equipped with many sensors, which in turn brings broad attack surface. Moreover, the execution environment of ADVs is often open and complex. Hence, ADVs are always at risk of safety and security threats. This paper proposes a fast method called Multi-IF, using multiple invocation features of system calls to detect anomalies in self-driving systems. Since self-driving functions take most of the computation resources and upgrade frequently, Multi-IF is designed to work under such resource constraints and support frequent updates. Given the collected sequences of system calls, the combination of different syntax patterns is used to analyze and construct feature vectors of those sequences. By taking the feature vectors as inputs, one-class support vector machine is adopted to determine whether the current sequence of system calls is abnormal, which is trained with the feature vectors from the normal sequences. The evaluations on both simulated and real data prove that the proposed method is effective in identifying the abnormal behavior after minutes of feature extraction and training. Further comparisons with the existing methods on the ADFA-LD data set also validate that the proposed approach achieves a higher accuracy with less time overhead.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multinomial Logit Bandit with Low Switching Cost

We study multinomial logit bandit with limited adaptivity, where the algorithms change their exploration actions as infrequently as possible when achieving almost optimal minimax regret. We propose two measures of adaptivity: the assortment switching cost and the more fine-grained item switching cost. We present an anytime algorithm (AT-DUCB) with $O(N \log T)$ assortment switches, almost matching the lower bound $Ω(\frac{N \log T}{ \log \log T})$. In the fixed-horizon setting, our algorithm FH-DUCB incurs $O(N \log \log T)$ assortment switches, matching the asymptotic lower bound. We also present the ESUCB algorithm with item switching cost $O(N \log^2 T)$.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Nearly Minimax-Optimal Regret for Linearly Parameterized Bandits

We study the linear contextual bandit problem with finite action sets. When the problem dimension is $d$, the time horizon is $T$, and there are $n \leq 2^{d/2}$ candidate actions per time period, we (1) show that the minimax expected regret is $Ω(\sqrt{dT (\log T) (\log n)})$ for every algorithm, and (2) introduce a Variable-Confidence-Level (VCL) SupLinUCB algorithm whose regret matches the lower bound up to iterated logarithmic factors. Our algorithmic result saves two $\sqrt{\log T}$ factors from previous analysis, and our information-theoretical lower bound also improves previous results by one $\sqrt{\log T}$ factor, revealing a regret scaling quite different from classical multi-armed bandits in which no logarithmic $T$ term is present in minimax regret. Our proof techniques include variable confidence levels and a careful analysis of layer sizes of SupLinUCB on the upper bound side, and delicately constructed adversarial sequences showing the tightness of elliptical potential lemmas on the lower bound side.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Phononic waveguide assisted steady state entanglement of SiV centers

Multiparticle entanglement is of great significance for quantum metrology and quantum information processing. We here present an efficient scheme to generate stable multiparticle entanglement in a solid state setup, where an array of silicon-vacancy centers are embedded in a quasi-one-dimensional acoustic diamond waveguide. In this scheme, the continuum of phonon modes induces a controllable dissipative coupling among the SiV centers. We show that, by an appropriate choice of the distance between the SiV centers, the dipole-dipole interactions can be switched off due to destructive interferences, thus realizing a Dicke superradiance model. This gives rise to an entangled steady state of SiV centers with high fidelities. The protocol provides a feasible setup for the generation of multiparticle entanglement in a solid state system.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Pooling Regularized Graph Neural Network for fMRI Biomarker Analysis

Understanding how certain brain regions relate to a specific neurological disorder has been an important area of neuroimaging research. A promising approach to identify the salient regions is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, e.g. brain networks constructed by functional magnetic resonance imaging (fMRI). We propose an interpretable GNN framework with a novel salient region selection mechanism to determine neurological brain biomarkers associated with disorders. Specifically, we design novel regularized pooling layers that highlight salient regions of interests (ROIs) so that we can infer which ROIs are important to identify a certain disease based on the node pooling scores calculated by the pooling layers. Our proposed framework, Pooling Regularized-GNN (PR-GNN), encourages reasonable ROI-selection and provides flexibility to preserve either individual- or group-level patterns. We apply the PR-GNN framework on a Biopoint Autism Spectral Disorder (ASD) fMRI dataset. We investigate different choices of the hyperparameters and show that PR-GNN outperforms baseline methods in terms of classification accuracy. The salient ROI detection results show high correspondence with the previous neuroimaging-derived biomarkers for ASD.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Soft-Root-Sign Activation Function

The choice of activation function in deep networks has a significant effect on the training dynamics and task performance. At present, the most effective and widely-used activation function is ReLU. However, because of the non-zero mean, negative missing and unbounded output, ReLU is at a potential disadvantage during optimization. To this end, we introduce a novel activation function to manage to overcome the above three challenges. The proposed nonlinearity, namely &#34;Soft-Root-Sign&#34; (SRS), is smooth, non-monotonic, and bounded. Notably, the bounded property of SRS distinguishes itself from most state-of-the-art activation functions. In contrast to ReLU, SRS can adaptively adjust the output by a pair of independent trainable parameters to capture negative information and provide zero-mean property, which leading not only to better generalization performance, but also to faster learning speed. It also avoids and rectifies the output distribution to be scattered in the non-negative real number space, making it more compatible with batch normalization (BN) and less sensitive to initialization. In experiments, we evaluated SRS on deep networks applied to a variety of tasks, including image classification, machine translation and generative modelling. Our SRS matches or exceeds models with ReLU and other state-of-the-art nonlinearities, showing that the proposed activation function is generalized and can achieve high performance across tasks. Ablation study further verified the compatibility with BN and self-adaptability for different initialization.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Stochastically Differentiable Probabilistic Programs

Probabilistic programs with mixed support (both continuous and discrete latent random variables) commonly appear in many probabilistic programming systems (PPSs). However, the existence of the discrete random variables prohibits many basic gradient-based inference engines, which makes the inference procedure on such models particularly challenging. Existing PPSs either require the user to manually marginalize out the discrete variables or to perform a composing inference by running inference separately on discrete and continuous variables. The former is infeasible in most cases whereas the latter has some fundamental shortcomings. We present a novel approach to run inference efficiently and robustly in such programs using stochastic gradient Markov Chain Monte Carlo family of algorithms. We compare our stochastic gradient-based inference algorithm against conventional baselines in several important cases of probabilistic programs with mixed support, and demonstrate that it outperforms existing composing inference baselines and works almost as well as inference in marginalized versions of the programs, but with less programming effort and at a lower computation cost.

0 citations0 reviewsNo code linkedOpen access
preprint2019arXiv

Quasicrystalline Chern Insulators

Chern insulator or quantum anomalous Hall state is a topological state with integer Hall conductivity but in absence of Landau level. It had been well established on various two-dimensional lattices with periodic structure. Here, we report similar Chern insulators can also be realized on the quasicrystal with $5$-fold rotational symmetry. Providing the staggered flux through plaquettes, we propose two types of quasicrystalline Chern insulators. Their topological characterizations are well identified by the robustness of edge states, non-zero real-space Chern number, and quantized conductance. We further find the failure of integer conductivity but with quantized Chern number at some special energies. Our study therefore provide a new opportunity to searching topological materials in aperiodic system.

0 citations0 reviewsNo code linkedOpen access