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

Tao Sun

Tao Sun contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningComputer VisionArtificial Intelligencecond-mat.mtrl-scieess.SYmath.OCRoboticsSystems and ControlApplicationsastro-ph.IMeess.ASMethodologyMultiagent SystemsMultimediaphysics.app-phphysics.chem-phphysics.comp-phphysics.ins-detphysics.soc-phSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
21works
0followers
20topics
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

21 published item(s)

preprint2026arXiv

Stability and Generalization for Decentralized Markov SGD

Stochastic gradient methods are central to large-scale learning, yet their generalization theory typically relies on independent sampling assumptions. In many practical applications, data are generated by Markov chains and learning is performed in a decentralized manner, which introduces significant analytical challenges. In this work, we investigate the stability and generalization of decentralized stochastic gradient descent (SGD) and stochastic gradient descent ascent (SGDA) under Markov chain sampling. Leveraging a stability-based framework, we characterize how Markovian dependence and decentralized communication jointly influence generalization behavior. Our analysis captures the effects of network topology, Markov chain mixing properties, and primal-dual dynamics. We establish non-asymptotic generalization bounds for both algorithms, extending existing results on Markov stochastic gradient methods to decentralized and minimax settings.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Unveiling High-Probability Generalization in Decentralized SGD

Decentralized stochastic gradient descent (D-SGD) is an efficient method for large-scale distributed learning. Existing generalization studies mainly address expected results, achieving rates limited to $\mathcal{O}\left(\frac{1}{δ\sqrt{mn}}\right)$, where $δ$ is the confidence parameter, $m$ the number of workers, and $n$ the sample size. When $m=1$, D-SGD reduces to traditional SGD, whose optimal high-probability generalization bound is $\mathcal{O}\left(\frac{1}{\sqrt{n}}\log (1/δ)\right)$. This discrepancy reveals a gap between high-probability guarantees for SGD and those for D-SGD. To close this, we develop a high-probability learning theory for D-SGD, aiming for the optimal $\mathcal{O}\left(\frac{1}{\sqrt{mn}}\log (1/δ)\right)$ rate. We refine bounds for D-SGD using pointwise uniform stability in distributed learning-a weaker notion than uniform stability-and analyze them across convex, strongly convex, and non-convex settings. We also provide high-probability results for gradient-based measures in non-convex cases where only local minima exist, and derive optimization error and excess risk bounds. Finally, accounting for communication overhead, we analyze generalization bounds for local models within time-varying frameworks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Incorporation of density scaling constraint in density functional design via contrastive representation learning

In a data-driven paradigm, machine learning (ML) is the central component for developing accurate and universal exchange-correlation (XC) functionals in density functional theory (DFT). It is well known that XC functionals must satisfy several exact conditions and physical constraints, such as density scaling, spin scaling, and derivative discontinuity. In this work, we demonstrate that contrastive learning is a computationally efficient and flexible method to incorporate a physical constraint in ML-based density functional design. We propose a schematic approach to incorporate the uniform density scaling property of electron density for exchange energies by adopting contrastive representation learning during the pretraining task. The pretrained hidden representation is transferred to the downstream task to predict the exchange energies calculated by DFT. The electron density encoder transferred from the pretraining task based on contrastive learning predicts exchange energies that satisfy the scaling property, while the model trained without using contrastive learning gives poor predictions for the scaling-transformed electron density systems. Furthermore, the model with pretrained encoder gives a satisfactory performance with only small fractions of the whole augmented dataset labeled, comparable to the model trained from scratch using the whole dataset. The results demonstrate that incorporating exact constraints through contrastive learning can enhance the understanding of density-energy mapping using neural network (NN) models with less data labeling, which will be beneficial to generalizing the application of NN-based XC functionals in a wide range of scenarios that are not always available experimentally but theoretically justified. This work represents a viable pathway toward the machine learning design of a universal density functional via representation learning.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On the Practicality of Deterministic Epistemic Uncertainty

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time. However, it remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications - both prerequisites for their practical deployment. To this end, we first provide a taxonomy of DUMs, and evaluate their calibration under continuous distributional shifts. Then, we extend them to semantic segmentation. We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Prior Knowledge Guided Unsupervised Domain Adaptation

The waive of labels in the target domain makes Unsupervised Domain Adaptation (UDA) an attractive technique in many real-world applications, though it also brings great challenges as model adaptation becomes harder without labeled target data. In this paper, we address this issue by seeking compensation from target domain prior knowledge, which is often (partially) available in practice, e.g., from human expertise. This leads to a novel yet practical setting where in addition to the training data, some prior knowledge about the target class distribution are available. We term the setting as Knowledge-guided Unsupervised Domain Adaptation (KUDA). In particular, we consider two specific types of prior knowledge about the class distribution in the target domain: Unary Bound that describes the lower and upper bounds of individual class probabilities, and Binary Relationship that describes the relations between two class probabilities. We propose a general rectification module that uses such prior knowledge to refine model generated pseudo labels. The module is formulated as a Zero-One Programming problem derived from the prior knowledge and a smooth regularizer. It can be easily plugged into self-training based UDA methods, and we combine it with two state-of-the-art methods, SHOT and DINE. Empirical results on four benchmarks confirm that the rectification module clearly improves the quality of pseudo labels, which in turn benefits the self-training stage. With the guidance from prior knowledge, the performances of both methods are substantially boosted. We expect our work to inspire further investigations in integrating prior knowledge in UDA. Code is available at https://github.com/tsun/KUDA.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

S3E-GNN: Sparse Spatial Scene Embedding with Graph Neural Networks for Camera Relocalization

Camera relocalization is the key component of simultaneous localization and mapping (SLAM) systems. This paper proposes a learning-based approach, named Sparse Spatial Scene Embedding with Graph Neural Networks (S3E-GNN), as an end-to-end framework for efficient and robust camera relocalization. S3E-GNN consists of two modules. In the encoding module, a trained S3E network encodes RGB images into embedding codes to implicitly represent spatial and semantic embedding code. With embedding codes and the associated poses obtained from a SLAM system, each image is represented as a graph node in a pose graph. In the GNN query module, the pose graph is transformed to form a embedding-aggregated reference graph for camera relocalization. We collect various scene datasets in the challenging environments to perform experiments. Our results demonstrate that S3E-GNN method outperforms the traditional Bag-of-words (BoW) for camera relocalization due to learning-based embedding and GNN powered scene matching mechanism.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Safe Self-Refinement for Transformer-based Domain Adaptation

Unsupervised Domain Adaptation (UDA) aims to leverage a label-rich source domain to solve tasks on a related unlabeled target domain. It is a challenging problem especially when a large domain gap lies between the source and target domains. In this paper we propose a novel solution named SSRT (Safe Self-Refinement for Transformer-based domain adaptation), which brings improvement from two aspects. First, encouraged by the success of vision transformers in various vision tasks, we arm SSRT with a transformer backbone. We find that the combination of vision transformer with simple adversarial adaptation surpasses best reported Convolutional Neural Network (CNN)-based results on the challenging DomainNet benchmark, showing its strong transferable feature representation. Second, to reduce the risk of model collapse and improve the effectiveness of knowledge transfer between domains with large gaps, we propose a Safe Self-Refinement strategy. Specifically, SSRT utilizes predictions of perturbed target domain data to refine the model. Since the model capacity of vision transformer is large and predictions in such challenging tasks can be noisy, a safe training mechanism is designed to adaptively adjust learning configuration. Extensive evaluations are conducted on several widely tested UDA benchmarks and SSRT achieves consistently the best performances, including 85.43% on Office-Home, 88.76% on VisDA-2017 and 45.2% on DomainNet.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation

Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, however, fall short of capturing the mutable nature of the real world. In this paper, we introduce the largest multi-task synthetic dataset for autonomous driving, SHIFT. It presents discrete and continuous shifts in cloudiness, rain and fog intensity, time of day, and vehicle and pedestrian density. Featuring a comprehensive sensor suite and annotations for several mainstream perception tasks, SHIFT allows investigating the degradation of a perception system performance at increasing levels of domain shift, fostering the development of continuous adaptation strategies to mitigate this problem and assess model robustness and generality. Our dataset and benchmark toolkit are publicly available at www.vis.xyz/shift.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Transition edge sensor based detector: from X-ray to $γ$-ray

The Transition Edge Sensor is extremely sensitive to the change of temperature, combined with the high-Z metal of a certain thickness, it can realize the high energy resolution measurement of particles such as X-rays. X-rays with energies below 10 keV have very weak penetrating ability, so only a few microns thick of gold or bismuth can obtain quantum efficiency higher than 70\%. Therefore, the entire structure of the TES X-ray detector in this energy range can be realized in the microfabrication process. However, for X-rays or gamma rays from 10 keV to 200 keV, sub-millimeter absorber layers are required, which cannot be realized by microfabrication process. This paper first briefly introduces a set of TES X-ray detectors and their auxiliary systems built by ShanghaiTech University, then focus on the introduction of the TES $γ$-ray detector, with absorber based on an sub-millimeter lead-tin alloy sphere. The detector has a quantum efficiency above 70\% near 100 keV, and an energy resolution of about 161.5eV@59.5keV.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Trend estimation and short-term forecasting of COVID-19 cases and deaths worldwide

Since the beginning of the COVID-19 pandemic, many dashboards have emerged as useful tools to monitor the evolution of the pandemic, inform the public, and assist governments in decision making. Our goal is to develop a globally applicable method, integrated in a twice daily updated dashboard that provides an estimate of the trend in the evolution of the number of cases and deaths from reported data of more than 200 countries and territories, as well as a seven-day forecast. One of the significant difficulties to manage a quickly propagating epidemic is that the details of the dynamic needed to forecast its evolution are obscured by the delays in the identification of cases and deaths and by irregular reporting. Our forecasting methodology substantially relies on estimating the underlying trend in the observed time series using robust seasonal trend decomposition techniques. This allows us to obtain forecasts with simple, yet effective extrapolation methods in linear or log scale. We present the results of an assessment of our forecasting methodology and discuss its application to the production of global and regional risk maps.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast

We present an approach to learn voice-face representations from the talking face videos, without any identity labels. Previous works employ cross-modal instance discrimination tasks to establish the correlation of voice and face. These methods neglect the semantic content of different videos, introducing false-negative pairs as training noise. Furthermore, the positive pairs are constructed based on the natural correlation between audio clips and visual frames. However, this correlation might be weak or inaccurate in a large amount of real-world data, which leads to deviating positives into the contrastive paradigm. To address these issues, we propose the cross-modal prototype contrastive learning (CMPC), which takes advantage of contrastive methods and resists adverse effects of false negatives and deviate positives. On one hand, CMPC could learn the intra-class invariance by constructing semantic-wise positives via unsupervised clustering in different modalities. On the other hand, by comparing the similarities of cross-modal instances from that of cross-modal prototypes, we dynamically recalibrate the unlearnable instances' contribution to overall loss. Experiments show that the proposed approach outperforms state-of-the-art unsupervised methods on various voice-face association evaluation protocols. Additionally, in the low-shot supervision setting, our method also has a significant improvement compared to previous instance-wise contrastive learning.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

End-to-end Full Projector Compensation

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and may suffer from suboptimal solutions. In this paper, we propose the first end-to-end differentiable solution, named CompenNeSt++, to solve the two problems jointly. First, we propose a novel geometric correction subnet, named WarpingNet, which is designed with a cascaded coarse-to-fine structure to learn the sampling grid directly from sampling images. Second, we propose a novel photometric compensation subnet, named CompenNeSt, which is designed with a siamese architecture to capture the photometric interactions between the projection surface and the projected images, and to use such information to compensate the geometrically corrected images. By concatenating WarpingNet with CompenNeSt, CompenNeSt++ accomplishes full projector compensation and is end-to-end trainable. Third, to improve practicability, we propose a novel synthetic data-based pre-training strategy to significantly reduce the number of training images and training time. Moreover, we construct the first setup-independent full compensation benchmark to facilitate future studies. In thorough experiments, our method shows clear advantages over prior art with promising compensation quality and meanwhile being practically convenient.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Inertial Proximal Deep Learning Alternating Minimization for Efficient Neutral Network Training

In recent years, the Deep Learning Alternating Minimization (DLAM), which is actually the alternating minimization applied to the penalty form of the deep neutral networks training, has been developed as an alternative algorithm to overcome several drawbacks of Stochastic Gradient Descent (SGD) algorithms. This work develops an improved DLAM by the well-known inertial technique, namely iPDLAM, which predicts a point by linearization of current and last iterates. To obtain further training speed, we apply a warm-up technique to the penalty parameter, that is, starting with a small initial one and increasing it in the iterations. Numerical results on real-world datasets are reported to demonstrate the efficiency of our proposed algorithm.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Stability and Generalization of the Decentralized Stochastic Gradient Descent

The stability and generalization of stochastic gradient-based methods provide valuable insights into understanding the algorithmic performance of machine learning models. As the main workhorse for deep learning, stochastic gradient descent has received a considerable amount of studies. Nevertheless, the community paid little attention to its decentralized variants. In this paper, we provide a novel formulation of the decentralized stochastic gradient descent. Leveraging this formulation together with (non)convex optimization theory, we establish the first stability and generalization guarantees for the decentralized stochastic gradient descent. Our theoretical results are built on top of a few common and mild assumptions and reveal that the decentralization deteriorates the stability of SGD for the first time. We verify our theoretical findings by using a variety of decentralized settings and benchmark machine learning models.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

The Phonon Quasiparticle Approach for Anharmonic Properties of Solids

Knowledge of lattice anharmonicity is essential to elucidate distinctive thermal properties in crystalline solids. Yet, accurate \textit{ab initio} investigations of lattice anharmonicity encounter difficulties owing to the cumbersome computations. Here we introduce the phonon quasiparticle approach and review its application to various materials. This method efficiently and reliably addresses lattice anharmonicity by combining \textit{ab initio} molecular dynamics and lattice dynamics calculations. Thus, in principle, it accounts for full anharmonic effects and overcomes finite-size effects typical of \textit{ab initio} molecular dynamics. The validity and effectiveness of the current approach are demonstrated in the computation of thermodynamic and heat transport properties of weakly and strongly anharmonic systems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Discovering universal scaling laws in 3D printing of metals with genetic programming and dimensional analysis

We leverage dimensional analysis and genetic programming (a type of machine learning) to discover two strikingly simple but universal scaling laws, which remain accurate for different materials, processing conditions, and machines in metal three-dimensional (3D) printing. The first one is extracted from high-fidelity high-speed synchrotron X-ray imaging, and defines a new dimensionless number, Keyhole number, to predict melt-pool vapor depression depth. The second predicts porosity using the Keyhole number and another dimensionless number, normalized energy density. By reducing the dimensions of these longstanding problems, the low-dimensional scaling laws will aid process optimization and defect elimination, and potentially lead to a quantitative predictive framework for the critical issues in metal 3D printing. Moreover, the method itself is broadly applicable to a range of scientific areas.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

FedGAN: Federated Generative Adversarial Networks for Distributed Data

We propose Federated Generative Adversarial Network (FedGAN) for training a GAN across distributed sources of non-independent-and-identically-distributed data sources subject to communication and privacy constraints. Our algorithm uses local generators and discriminators which are periodically synced via an intermediary that averages and broadcasts the generator and discriminator parameters. We theoretically prove the convergence of FedGAN with both equal and two time-scale updates of generator and discriminator, under standard assumptions, using stochastic approximations and communication efficient stochastic gradient descents. We experiment FedGAN on toy examples (2D system, mixed Gaussian, and Swiss role), image datasets (MNIST, CIFAR-10, and CelebA), and time series datasets (household electricity consumption and electric vehicle charging sessions). We show FedGAN converges and has similar performance to general distributed GAN, while reduces communication complexity. We also show its robustness to reduced communications.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Power and the Pandemic: Exploring Global Changes in Electricity Demand During COVID-19

Understanding how efforts to limit exposure to COVID-19 have altered electricity demand provides insights not only into how dramatic restrictions shape electricity demand but also about future electricity use in a post-COVID-19 world. We develop a unified modeling framework to quantify and compare electricity usage changes in 58 countries and regions around the world from January-May 2020. We find that daily electricity demand declined as much as 10% in April 2020 compared to modelled demand, controlling for weather, seasonal and temporal effects, but with significant variation. Clustering techniques show that four impact groups capture systematic differences in timing and depth of electricity usage changes, ranging from a mild decline of 2% to an extreme decline of 26%. These groupings do not align with geography, with almost every continent having at least one country or region that experienced a dramatic reduction in demand and one that did not. Instead, we find that such changes relate to government restrictions and mobility. Government restrictions have a non-linear effect on demand that generally saturates at its most restrictive levels and sustains even as restrictions ease. Mobility offers a sharper focus on electricity demand change with workplace and residential mobility strongly linked to demand changes at the daily level. Steep declines in electricity usage are associated with workday hourly load patterns that resemble pre-COVID weekend usage. Quantifying these impacts is a crucial first step in understanding the impacts of crises like the pandemic and the associated societal response on electricity demand.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Three-quarter Sibling Regression for Denoising Observational Data

Many ecological studies and conservation policies are based on field observations of species, which can be affected by systematic variability introduced by the observation process. A recently introduced causal modeling technique called 'half-sibling regression' can detect and correct for systematic errors in measurements of multiple independent random variables. However, it will remove intrinsic variability if the variables are dependent, and therefore does not apply to many situations, including modeling of species counts that are controlled by common causes. We present a technique called 'three-quarter sibling regression' to partially overcome this limitation. It can filter the effect of systematic noise when the latent variables have observed common causes. We provide theoretical justification of this approach, demonstrate its effectiveness on synthetic data, and show that it reduces systematic detection variability due to moon brightness in moth surveys.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

TraceCaps: A Capsule-based Neural Network for Semantic Segmentation

In this paper, we propose a capsule-based neural network model to solve the semantic segmentation problem. By taking advantage of the extractable part-whole dependencies available in capsule layers, we derive the probabilities of the class labels for individual capsules through a recursive, layer-by-layer procedure. We model this procedure as a traceback pipeline and take it as a central piece to build an end-to-end segmentation network. Under the proposed framework, image-level class labels and object boundaries are jointly sought in an explicit manner, which poses a significant advantage over the state-of-the-art fully convolutional network (FCN) solutions. With the capability to extracted part-whole information, our traceback pipeline can potentially be utilized as the building blocks to design interpretable neural networks. Experiments conducted on modified MNIST and neuroimages demonstrate that our model considerably enhance the segmentation performance compared to the leading FCN variants.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks

Simulation-to-simulation and simulation-to-real world transfer of neural network models have been a difficult problem. To close the reality gap, prior methods to simulation-to-real world transfer focused on domain adaptation, decoupling perception and dynamics and solving each problem separately, and randomization of agent parameters and environment conditions to expose the learning agent to a variety of conditions. While these methods provide acceptable performance, the computational complexity required to capture a large variation of parameters for comprehensive scenarios on a given task such as autonomous driving or robotic manipulation is high. Our key contribution is to theoretically prove and empirically demonstrate that a deep attention convolutional neural network (DACNN) with specific visual sensor configuration performs as well as training on a dataset with high domain and parameter variation at lower computational complexity. Specifically, the attention network weights are learned through policy optimization to focus on local dependencies that lead to optimal actions, and does not require tuning in real-world for generalization. Our new architecture adapts perception with respect to the control objective, resulting in zero-shot learning without pre-training a perception network. To measure the impact of our new deep network architecture on domain adaptation, we consider autonomous driving as a use case. We perform an extensive set of experiments in simulation-to-simulation and simulation-to-real scenarios to compare our approach to several baselines including the current state-of-art models.

0 citations0 reviewsNo code linkedOpen access