Research connected to "machine learning"

Search papers, authors, topics, institutions and opportunities, then move straight into the graph around the result.

Search results

Showing works 993-1,024 from 49,008 works in Machine Learning. Use pages to browse more, or open the graph for the map.

49,008matching works

Shown33 Papers32

Full topic scaleMachine Learning

49,008 works and 109,744 authors are indexed for this topic. This page shows 32 works at a time so search stays fast.

Open topic Open graph

Match modeExact match focus

Semantic hits0

Active filters0

Graph viewOpen

Useful next jumps

Multi-Task Regularization with Covariance Dictionary for Linear Classifiersworkpreprint / 2013 / arXiv EEF: Exponentially Embedded Families with Class-Specific Features for Classificationworkpreprint / 2016 / arXiv Analytical bounds on the local Lipschitz constants of affine-ReLU functionsworkpreprint / 2020 / arXiv Machine Learningtopic49008 works

preprint2013arXiv

Multi-Task Regularization with Covariance Dictionary for Linear Classifiers

In this paper we propose a multi-task linear classifier learning problem called D-SVM (Dictionary SVM). D-SVM uses a dictionary of parameter covariance shared by all tasks to do multi-task knowledge transfer among different tasks. We formally define the learning problem of D-SVM and show two interpretations of this problem, from both the probabilistic and kernel perspectives. From the probabilistic perspective, we show that our learning formulation is actually a MAP estimation on all optimization variables. We also show its equivalence to a multiple kernel learning problem in which one is trying to find a re-weighting kernel for features from a dictionary of basis (despite the fact that only linear classifiers are learned). Finally, we describe an alternative optimization scheme to minimize the objective function and present empirical studies to valid our algorithm.

preprint2016arXiv

EEF: Exponentially Embedded Families with Class-Specific Features for Classification

In this letter, we present a novel exponentially embedded families (EEF) based classification method, in which the probability density function (PDF) on raw data is estimated from the PDF on features. With the PDF construction, we show that class-specific features can be used in the proposed classification method, instead of a common feature subset for all classes as used in conventional approaches. We apply the proposed EEF classifier for text categorization as a case study and derive an optimal Bayesian classification rule with class-specific feature selection based on the Information Gain (IG) score. The promising performance on real-life data sets demonstrates the effectiveness of the proposed approach and indicates its wide potential applications.

preprint2020arXiv

Analytical bounds on the local Lipschitz constants of affine-ReLU functions

In this paper, we determine analytical bounds on the local Lipschitz constants of of affine functions composed with rectified linear units (ReLUs). Affine-ReLU functions represent a widely used layer in deep neural networks, due to the fact that convolution, fully-connected, and normalization functions are all affine, and are often followed by a ReLU activation function. Using an analytical approach, we mathematically determine upper bounds on the local Lipschitz constant of an affine-ReLU function, show how these bounds can be combined to determine a bound on an entire network, and discuss how the bounds can be efficiently computed, even for larger layers and networks. We show several examples by applying our results to AlexNet, as well as several smaller networks based on the MNIST and CIFAR-10 datasets. The results show that our method produces tighter bounds than the standard conservative bound (i.e. the product of the spectral norms of the layers' linear matrices), especially for small perturbations.

preprint2022arXiv

GrASP: Gradient-Based Affordance Selection for Planning

Planning with a learned model is arguably a key component of intelligence. There are several challenges in realizing such a component in large-scale reinforcement learning (RL) problems. One such challenge is dealing effectively with continuous action spaces when using tree-search planning (e.g., it is not feasible to consider every action even at just the root node of the tree). In this paper we present a method for selecting affordances useful for planning -- for learning which small number of actions/options from a continuous space of actions/options to consider in the tree-expansion process during planning. We consider affordances that are goal-and-state-conditional mappings to actions/options as well as unconditional affordances that simply select actions/options available in all states. Our selection method is gradient based: we compute gradients through the planning procedure to update the parameters of the function that represents affordances. Our empirical work shows that it is feasible to learn to select both primitive-action and option affordances, and that simultaneously learning to select affordances and planning with a learned value-equivalent model can outperform model-free RL.

preprint2020arXiv

Combining Ensemble Kalman Filter and Reservoir Computing to predict spatio-temporal chaotic systems from imperfect observations and models

Prediction of spatio-temporal chaotic systems is important in various fields, such as Numerical Weather Prediction (NWP). While data assimilation methods have been applied in NWP, machine learning techniques, such as Reservoir Computing (RC), are recently recognized as promising tools to predict spatio-temporal chaotic systems. However, the sensitivity of the skill of the machine learning based prediction to the imperfectness of observations is unclear. In this study, we evaluate the skill of RC with noisy and sparsely distributed observations. We intensively compare the performances of RC and Local Ensemble Transform Kalman Filter (LETKF) by applying them to the prediction of the Lorenz 96 system. Although RC can successfully predict the Lorenz 96 system if the system is perfectly observed, we find that RC is vulnerable to observation sparsity compared with LETKF. To overcome this limitation of RC, we propose to combine LETKF and RC. In our proposed method, the system is predicted by RC that learned the analysis time series estimated by LETKF. Our proposed method can successfully predict the Lorenz 96 system using noisy and sparsely distributed observations. Most importantly, our

preprint2022arXiv

A Manifold-based Airfoil Geometric-feature Extraction and Discrepant Data Fusion Learning Method

Geometrical shape of airfoils, together with the corresponding flight conditions, are crucial factors for aerodynamic performances prediction. The obtained airfoils geometrical features in most existing approaches (e.g., geometrical parameters extraction, polynomial description and deep learning) are in Euclidean space. State-of-the-art studies showed that curves or surfaces of an airfoil formed a manifold in Riemannian space. Therefore, the features extracted by existing methods are not sufficient to reflect the geometric-features of airfoils. Meanwhile, flight conditions and geometric features are greatly discrepant with different types, the relevant knowledge of the influence of these two factors that on final aerodynamic performances predictions must be evaluated and learned to improve prediction accuracy. Motivated by the advantages of manifold theory and multi-task learning, we propose a manifold-based airfoil geometric-feature extraction and discrepant data fusion learning method (MDF) to extract geometric-features of airfoils in Riemannian space (we call them manifold-features) and further fuse the manifold-features with flight conditions to predict aerodynamic performances. Experimental results show that our method could extract geometric-features of airfoils more accurately compared with existing methods, that the average MSE of re-built airfoils is reduced by 56.33%, and while keeping the same predicted accuracy level of CL, the MSE of CD predicted by MDF is further reduced by 35.37%.

preprint2022arXiv

Tractable Dendritic RNNs for Reconstructing Nonlinear Dynamical Systems

In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic behavior and noise. Previous deep learning approaches toward this goal often suffered from a lack of interpretability and tractability. In particular, the high-dimensional latent spaces often required for a faithful embedding, even when the underlying dynamics lives on a lower-dimensional manifold, can hamper theoretical analysis. Motivated by the emerging principles of dendritic computation, we augment a dynamically interpretable and mathematically tractable piecewise-linear (PL) recurrent neural network (RNN) by a linear spline basis expansion. We show that this approach retains all the theoretically appealing properties of the simple PLRNN, yet boosts its capacity for approximating arbitrary nonlinear dynamical systems in comparatively low dimensions. We employ two frameworks for training the system, one combining back-propagation-through-time (BPTT) with teacher forcing, and another based on fast and scalable variational inference. We show that the dendritically expanded PLRNN achieves better reconstructions with fewer parameters and dimensions on various dynamical systems benchmarks and compares favorably to other methods, while retaining a tractable and interpretable structure.

preprint2022arXiv

Active Source Free Domain Adaptation

Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data. However, the SFDA setting faces an effect bottleneck due to the absence of source data and target supervised information, as evidenced by the limited performance gains of newest SFDA methods. In this paper, for the first time, we introduce a more practical scenario called active source free domain adaptation (ASFDA) that permits actively selecting a few target data to be labeled by experts. To achieve that, we first find that those satisfying the properties of neighbor-chaotic, individual-different, and target-like are the best points to select, and we define them as the minimum happy (MH) points. We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points. We design three unique strategies: neighbor ambient uncertainty, neighbor diversity relaxation, and one-shot querying, to explore the MH points. Further, to fully exploit MH points in the learning process, we design a neighbor focal loss that assigns the weighted neighbor purity to the cross-entropy loss of MH points to make the model focus more on them. Extensive experiments verify that MHPL remarkably exceeds the various types of baselines and achieves significant performance gains at a small cost of labeling.

preprint2016arXiv

Online Learning with Feedback Graphs Without the Graphs

We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is \emph{never fully revealed} to the learner. We show a large gap between the adversarial and the stochastic cases. In the adversarial case, we prove that even for dense feedback graphs, the learner cannot improve upon a trivial regret bound obtained by ignoring any additional feedback besides her own loss. In contrast, in the stochastic case we give an algorithm that achieves $\widetilde Θ(\sqrt{αT})$ regret over $T$ rounds, provided that the independence numbers of the hidden feedback graphs are at most $α$. We also extend our results to a more general feedback model, in which the learner does not necessarily observe her own loss, and show that, even in simple cases, concealing the feedback graphs might render a learnable problem unlearnable.

preprint2022arXiv

Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear attention and hashing tricks; efficient transformers have been proposed to reduce the quadratic complexity of transformers but significantly degrade the accuracy. In response, we first interpret the linear attention and residual connections in computing the attention map as gradient descent steps. We then introduce momentum into these components and propose the \emph{momentum transformer}, which utilizes momentum to improve the accuracy of linear transformers while maintaining linear memory and computational complexities. Furthermore, we develop an adaptive strategy to compute the momentum value for our model based on the optimal momentum for quadratic optimization. This adaptive momentum eliminates the need to search for the optimal momentum value and further enhances the performance of the momentum transformer. A range of experiments on both autoregressive and non-autoregressive tasks, including image generation and machine translation, demonstrate that the momentum transformer outperforms popular linear transformers in training efficiency and accuracy.

preprint2020arXiv

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

In recent years, reinforcement learning (RL) systems with general goals beyond a cumulative sum of rewards have gained traction, such as in constrained problems, exploration, and acting upon prior experiences. In this paper, we consider policy optimization in Markov Decision Problems, where the objective is a general concave utility function of the state-action occupancy measure, which subsumes several of the aforementioned examples as special cases. Such generality invalidates the Bellman equation. As this means that dynamic programming no longer works, we focus on direct policy search. Analogously to the Policy Gradient Theorem \cite{sutton2000policy} available for RL with cumulative rewards, we derive a new Variational Policy Gradient Theorem for RL with general utilities, which establishes that the parametrized policy gradient may be obtained as the solution of a stochastic saddle point problem involving the Fenchel dual of the utility function. We develop a variational Monte Carlo gradient estimation algorithm to compute the policy gradient based on sample paths. We prove that the variational policy gradient scheme converges globally to the optimal policy for the general objec

preprint2026arXiv

HiGP: A high-performance Python package for Gaussian Process

Gaussian Processes (GPs) are flexible, nonparametric Bayesian models widely used for regression and classification because of their ability to capture complex data patterns and quantify predictive uncertainty. However, the O(n^3) computational cost of kernel matrix operations poses a major obstacle to applying GPs at scale. HiGP is a high-performance Python package designed to overcome these scalability limitations through advanced numerical linear algebra and hierarchical kernel representations. It integrates H^2 matrices to achieve near-linear complexity in both storage and computation for spatial datasets, supports on-the-fly kernel evaluation to avoid explicit storage in large-scale problems, and incorporates a robust Adaptive Factorized Nyström (AFN) preconditioner that accelerates convergence of iterative solvers across a broad range of kernel spectra. These computational kernels are implemented in C++ for maximum performance and exposed through Python interfaces, enabling seamless integration with modern machine learning workflows. HiGP also includes analytically derived gradient computations for efficient hyperparameter optimization, avoiding the inefficiencies of automatic

preprint2022arXiv

Robustness and Accuracy Could Be Reconcilable by (Proper) Definition

The trade-off between robustness and accuracy has been widely studied in the adversarial literature. Although still controversial, the prevailing view is that this trade-off is inherent, either empirically or theoretically. Thus, we dig for the origin of this trade-off in adversarial training and find that it may stem from the improperly defined robust error, which imposes an inductive bias of local invariance -- an overcorrection towards smoothness. Given this, we advocate employing local equivariance to describe the ideal behavior of a robust model, leading to a self-consistent robust error named SCORE. By definition, SCORE facilitates the reconciliation between robustness and accuracy, while still handling the worst-case uncertainty via robust optimization. By simply substituting KL divergence with variants of distance metrics, SCORE can be efficiently minimized. Empirically, our models achieve top-rank performance on RobustBench under AutoAttack. Besides, SCORE provides instructive insights for explaining the overfitting phenomenon and semantic input gradients observed on robust models. Code is available at https://github.com/P2333/SCORE.

preprint2021arXiv

CORE: A Knowledge Graph Entity Type Prediction Method via Complex Space Regression and Embedding

Entity type prediction is an important problem in knowledge graph (KG) research. A new KG entity type prediction method, named CORE (COmplex space Regression and Embedding), is proposed in this work. The proposed CORE method leverages the expressive power of two complex space embedding models; namely, RotatE and ComplEx models. It embeds entities and types in two different complex spaces using either RotatE or ComplEx. Then, we derive a complex regression model to link these two spaces. Finally, a mechanism to optimize embedding and regression parameters jointly is introduced. Experiments show that CORE outperforms benchmarking methods on representative KG entity type inference datasets. Strengths and weaknesses of various entity type prediction methods are analyzed.

preprint2021arXiv

Convolutional conditional neural processes for local climate downscaling

A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow deep learning techniques to be applied to off-the-grid spatio-temporal data. This model has a substantial advantage over existing downscaling methods in that the trained model can be used to generate multisite predictions at an arbitrary set of locations, regardless of the availability of training data. The convCNP model is shown to outperform an ensemble of existing downscaling techniques over Europe for both temperature and precipitation taken from the VALUE intercomparison project. The model also outperforms an approach that uses Gaussian processes to interpolate single-site downscaling models at unseen locations. Importantly, substantial improvement is seen in the representation of extreme precipitation events. These results indicate that the convCNP is a robust downscaling model suitable for generating localised projections for use in climate impact studies, and motivates further research into applications of deep learning techniques in statistical downscaling.

preprint2012arXiv

A robust and sparse K-means clustering algorithm

In many situations where the interest lies in identifying clusters one might expect that not all available variables carry information about these groups. Furthermore, data quality (e.g. outliers or missing entries) might present a serious and sometimes hard-to-assess problem for large and complex datasets. In this paper we show that a small proportion of atypical observations might have serious adverse effects on the solutions found by the sparse clustering algorithm of Witten and Tibshirani (2010). We propose a robustification of their sparse K-means algorithm based on the trimmed K-means algorithm of Cuesta-Albertos et al. (1997) Our proposal is also able to handle datasets with missing values. We illustrate the use of our method on microarray data for cancer patients where we are able to identify strong biological clusters with a much reduced number of genes. Our simulation studies show that, when there are outliers in the data, our robust sparse K-means algorithm performs better than other competing methods both in terms of the selection of features and also the identified clusters. This robust sparse K-means algorithm is implemented in the R package RSKC which is publicly ava

preprint2022arXiv

Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer

A reliable and efficient representation of multivariate time series is crucial in various downstream machine learning tasks. In multivariate time series forecasting, each variable depends on its historical values and there are inter-dependencies among variables as well. Models have to be designed to capture both intra- and inter-relationships among the time series. To move towards this goal, we propose the Time Series Attention Transformer (TSAT) for multivariate time series representation learning. Using TSAT, we represent both temporal information and inter-dependencies of multivariate time series in terms of edge-enhanced dynamic graphs. The intra-series correlations are represented by nodes in a dynamic graph; a self-attention mechanism is modified to capture the inter-series correlations by using the super-empirical mode decomposition (SMD) module. We applied the embedded dynamic graphs to times series forecasting problems, including two real-world datasets and two benchmark datasets. Extensive experiments show that TSAT clearly outerperforms six state-of-the-art baseline methods in various forecasting horizons. We further visualize the embedded dynamic graphs to illustrate the graph representation power of TSAT. We share our code at https://github.com/RadiantResearch/TSAT.

preprint2026arXiv

Reliability Under Randomness: An Empirical Analysis of Sparse and Dense Language Models Across Decoding Temperatures

The increasing prevalence of sparse Mixture-of-Experts (MoE) architectures in large language models raises important questions regarding their reliability under stochastic decoding. While conditional computation enables substantial gains in computational efficiency, it remains unclear whether the interaction between sparse routing and temperature-based sampling compromises output stability relative to dense architectures. This work investigates whether conditional computation in MoE models amplifies decoding-induced randomness, leading to reduced reliability as temperature increases. We evaluate three representative models: OLMoE-7B (sparse base), Mixtral-8x7B (sparse instruction-tuned), and Qwen2.5-3B (dense instruction-tuned) on deterministic arithmetic reasoning tasks with objectively verifiable answers. Experiments span four decoding configurations, ranging from greedy decoding to T=1.0. Our evaluation encompasses accuracy, format compliance, output consistency across repeated generations, and confidence metrics, totaling 9,360 model generations. Results demonstrate that the sparse instruction-tuned model exhibits stability comparable to the dense instruction-tuned model across

preprint2022arXiv

Neural Link Prediction with Walk Pooling

Graph neural networks achieve high accuracy in link prediction by jointly leveraging graph topology and node attributes. Topology, however, is represented indirectly; state-of-the-art methods based on subgraph classification label nodes with distance to the target link, so that, although topological information is present, it is tempered by pooling. This makes it challenging to leverage features like loops and motifs associated with network formation mechanisms. We propose a link prediction algorithm based on a new pooling scheme called WalkPool. WalkPool combines the expressivity of topological heuristics with the feature-learning ability of neural networks. It summarizes a putative link by random walk probabilities of adjacent paths. Instead of extracting transition probabilities from the original graph, it computes the transition matrix of a "predictive" latent graph by applying attention to learned features; this may be interpreted as feature-sensitive topology fingerprinting. WalkPool can leverage unsupervised node features or be combined with GNNs and trained end-to-end. It outperforms state-of-the-art methods on all common link prediction benchmarks, both homophilic and heterophilic, with and without node attributes. Applying WalkPool to a set of unsupervised GNNs significantly improves prediction accuracy, suggesting that it may be used as a general-purpose graph pooling scheme.

preprint2022arXiv

PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processes

Graph Neural Networks (GNNs) are widely adopted in advanced AI systems due to their capability of representation learning on graph data. Even though GNN explanation is crucial to increase user trust in the systems, it is challenging due to the complexity of GNN execution. Lately, many works have been proposed to address some of the issues in GNN explanation. However, they lack generalization capability or suffer from computational burden when the size of graphs is enormous. To address these challenges, we propose a multi-level GNN explanation framework based on an observation that GNN is a multimodal learning process of multiple components in graph data. The complexity of the original problem is relaxed by breaking into multiple sub-parts represented as a hierarchical structure. The top-level explanation aims at specifying the contribution of each component to the model execution and predictions, while fine-grained levels focus on feature attribution and graph structure attribution analysis based on knowledge distillation. Student models are trained in standalone modes and are responsible for capturing different teacher behaviors, later used for particular component interpretation. Besides, we also aim for personalized explanations as the framework can generate different results based on user preferences. Finally, extensive experiments demonstrate the effectiveness and fidelity of our proposed approach.

preprint2016arXiv

Distributed Multi-Task Learning with Shared Representation

We study the problem of distributed multi-task learning with shared representation, where each machine aims to learn a separate, but related, task in an unknown shared low-dimensional subspaces, i.e. when the predictor matrix has low rank. We consider a setting where each task is handled by a different machine, with samples for the task available locally on the machine, and study communication-efficient methods for exploiting the shared structure.

preprint2010arXiv

Measuring Latent Causal Structure

Discovering latent representations of the observed world has become increasingly more relevant in data analysis. Much of the effort concentrates on building latent variables which can be used in prediction problems, such as classification and regression. A related goal of learning latent structure from data is that of identifying which hidden common causes generate the observations, such as in applications that require predicting the effect of policies. This will be the main problem tackled in our contribution: given a dataset of indicators assumed to be generated by unknown and unmeasured common causes, we wish to discover which hidden common causes are those, and how they generate our data. This is possible under the assumption that observed variables are linear functions of the latent causes with additive noise. Previous results in the literature present solutions for the case where each observed variable is a noisy function of a single latent variable. We show how to extend the existing results for some cases where observed variables measure more than one latent variable.

preprint2012arXiv

A consistent adjacency spectral embedding for stochastic blockmodel graphs

We present a method to estimate block membership of nodes in a random graph generated by a stochastic blockmodel. We use an embedding procedure motivated by the random dot product graph model, a particular example of the latent position model. The embedding associates each node with a vector; these vectors are clustered via minimization of a square error criterion. We prove that this method is consistent for assigning nodes to blocks, as only a negligible number of nodes will be mis-assigned. We prove consistency of the method for directed and undirected graphs. The consistent block assignment makes possible consistent parameter estimation for a stochastic blockmodel. We extend the result in the setting where the number of blocks grows slowly with the number of nodes. Our method is also computationally feasible even for very large graphs. We compare our method to Laplacian spectral clustering through analysis of simulated data and a graph derived from Wikipedia documents.

preprint2022arXiv

Self-supervised Learning for Label Sparsity in Computational Drug Repositioning

The computational drug repositioning aims to discover new uses for marketed drugs, which can accelerate the drug development process and play an important role in the existing drug discovery system. However, the number of validated drug-disease associations is scarce compared to the number of drugs and diseases in the real world. Too few labeled samples will make the classification model unable to learn effective latent factors of drugs, resulting in poor generalization performance. In this work, we propose a multi-task self-supervised learning framework for computational drug repositioning. The framework tackles label sparsity by learning a better drug representation. Specifically, we take the drug-disease association prediction problem as the main task, and the auxiliary task is to use data augmentation strategies and contrast learning to mine the internal relationships of the original drug features, so as to automatically learn a better drug representation without supervised labels. And through joint training, it is ensured that the auxiliary task can improve the prediction accuracy of the main task. More precisely, the auxiliary task improves drug representation and serving as additional regularization to improve generalization. Furthermore, we design a multi-input decoding network to improve the reconstruction ability of the autoencoder model. We evaluate our model using three real-world datasets. The experimental results demonstrate the effectiveness of the multi-task self-supervised learning framework, and its predictive ability is superior to the state-of-the-art model.

preprint2021arXiv

Safe Distributional Reinforcement Learning

Safety in reinforcement learning (RL) is a key property in both training and execution in many domains such as autonomous driving or finance. In this paper, we formalize it with a constrained RL formulation in the distributional RL setting. Our general model accepts various definitions of safety(e.g., bounds on expected performance, CVaR, variance, or probability of reaching bad states). To ensure safety during learning, we extend a safe policy optimization method to solve our problem. The distributional RL perspective leads to a more efficient algorithm while additionally catering for natural safe constraints. We empirically validate our propositions on artificial and real domains against appropriate state-of-the-art safe RL algorithms.

preprint2020arXiv

Region-Wise Attack: On Efficient Generation of Robust Physical Adversarial Examples

Deep neural networks (DNNs) are shown to be susceptible to adversarial example attacks. Most existing works achieve this malicious objective by crafting subtle pixel-wise perturbations, and they are difficult to launch in the physical world due to inevitable transformations (e.g., different photographic distances and angles). Recently, there are a few research works on generating physical adversarial examples, but they generally require the details of the model a priori, which is often impractical. In this work, we propose a novel physical adversarial attack for arbitrary black-box DNN models, namely Region-Wise Attack. To be specific, we present how to efficiently search for regionwise perturbations to the inputs and determine their shapes, locations and colors via both top-down and bottom-up techniques. In addition, we introduce two fine-tuning techniques to further improve the robustness of our attack. Experimental results demonstrate the efficacy and robustness of the proposed Region-Wise Attack in real world.

preprint2020arXiv

Fiber: A Platform for Efficient Development and Distributed Training for Reinforcement Learning and Population-Based Methods

Recent advances in machine learning are consistently enabled by increasing amounts of computation. Reinforcement learning (RL) and population-based methods in particular pose unique challenges for efficiency and flexibility to the underlying distributed computing frameworks. These challenges include frequent interaction with simulations, the need for dynamic scaling, and the need for a user interface with low adoption cost and consistency across different backends. In this paper we address these challenges while still retaining development efficiency and flexibility for both research and practical applications by introducing Fiber, a scalable distributed computing framework for RL and population-based methods. Fiber aims to significantly expand the accessibility of large-scale parallel computation to users of otherwise complicated RL and population-based approaches without the need to for specialized computational expertise.

preprint2021arXiv

SplitBrain: Hybrid Data and Model Parallel Deep Learning

The recent success of deep learning applications has coincided with those widely available powerful computational resources for training sophisticated machine learning models with huge datasets. Nonetheless, training large models such as convolutional neural networks using model parallelism (as opposed to data parallelism) is challenging because the complex nature of communication between model shards makes it difficult to partition the computation efficiently across multiple machines with an acceptable trade-off. This paper presents SplitBrain, a high performance distributed deep learning framework supporting hybrid data and model parallelism. Specifically, SplitBrain provides layer-specific partitioning that co-locates compute intensive convolutional layers while sharding memory demanding layers. A novel scalable group communication is proposed to further improve the training throughput with reduced communication overhead. The results show that SplitBrain can achieve nearly linear speedup while saving up to 67\% of memory consumption for data and model parallel VGG over CIFAR-10.

preprint2020arXiv

Graph Structured Prediction Energy Networks

For joint inference over multiple variables, a variety of structured prediction techniques have been developed to model correlations among variables and thereby improve predictions. However, many classical approaches suffer from one of two primary drawbacks: they either lack the ability to model high-order correlations among variables while maintaining computationally tractable inference, or they do not allow to explicitly model known correlations. To address this shortcoming, we introduce `Graph Structured Prediction Energy Networks,' for which we develop inference techniques that allow to both model explicit local and implicit higher-order correlations while maintaining tractability of inference. We apply the proposed method to tasks from the natural language processing and computer vision domain and demonstrate its general utility.

preprint2026arXiv

Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity

Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized architectures. Mechanistic interpretability has led to the development of various methods for assessing layer relevance, with cosine similarity being a widely used tool in the field. On this work, we demonstrate that cosine similarity is a poor proxy for the actual performance degradation caused by layer removal. Our theoretical analysis shows that a layer can exhibit an arbitrarily low cosine similarity score while still being crucial to the model's performance. On the other hand, empirical evidence from a range of LLMs confirms that the correlation between cosine similarity and actual performance degradation is often weak or moderate, leading to misleading interpretations of a transformer's internal mechanisms. We propose a more robust metric for assessing layer relevance: the actual drop in model accuracy resulting from the removal of a layer. Even though it is a computationally costly metric, this approach offers a more accurate picture of layer importance, allowing for more informed pruning strategies and lightweight models. Our findings have significant implications for the development of interpretable LLMs and highlight the need to move beyond cosine similarity in assessing layer relevance.

preprint2026arXiv

Semantic State Abstraction Interfaces for LLM-Augmented Portfolio Decisions: Multi-Axis News Decomposition and RL Diagnostics

We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into $K$ auditable, named coordinates with neutral defaults on no-news days, designed to separate representation hypotheses from optimisation variance in sequential decision systems. Our contribution is the framework and its evaluation protocol, not a claim that SSAI outperforms denser alternatives. We instantiate SSAI with $K=4$ axes (sentiment, risk, confidence, volatility forecast) on a US-equity panel (30 NASDAQ-100 names, FNSPID news, 2019--2023 test), and evaluate it across direct factor portfolios, supervised ridge forecasters, and RL agents (DP-PPO, SAC) that share the same fixed $φ$. The four-factor factor portfolio reaches 307.2% cumulative return and Sharpe 1.067, but apparent gains versus buy-and-hold (243.6%) fail coverage-stratified controls, reverse at $\geq 0.2$% costs, and are statistically fragile versus a sentiment-only baseline; a PC1 composite and a FinBERT portfolio baseline are stronger ranking signals in this setting. Ridge and RL blocks diagnose representation versus optimiser effects. We position SSAI as an interpretability-performance diagnostic and reusable protocol for sparse-text decision systems.

preprint2020arXiv

Ordering Dimensions with Nested Dropout Normalizing Flows

The latent space of normalizing flows must be of the same dimensionality as their output space. This constraint presents a problem if we want to learn low-dimensional, semantically meaningful representations. Recent work has provided compact representations by fitting flows constrained to manifolds, but hasn't defined a density off that manifold. In this work we consider flows with full support in data space, but with ordered latent variables. Like in PCA, the leading latent dimensions define a sequence of manifolds that lie close to the data. We note a trade-off between the flow likelihood and the quality of the ordering, depending on the parameterization of the flow.