Machine Learning

This paper introduces uniform meta-stability for meta-learning, providing tighter generalization bounds for convex and weakly-convex problems, addressing computational limitations of existing algorith…

Giant leap in molecular GNNs! MolGPS, a new foundation model, achieves state-of-the-art performance on molecular property prediction by leveraging massive datasets and demonstrating the scalability o…

Boosting certified robustness of machine learning models by 3-4% using generated data from diffusion models!

New reinforcement learning model clarifies the role of information structure in partially-observable sequential decision-making problems, proving an upper bound on learning complexity.

Fragile SGD & Amelie SGD achieve near-optimal speed in decentralized asynchronous optimization, handling diverse worker & communication speeds.

Federated online model selection needs collaboration only when clients have limited computing power; otherwise, independent learning suffices.

This paper provides novel algorithms and matching lower bounds for multi-armed bandits with expert advice and contextual linear bandits, resolving open questions and advancing theoretical understandin…

Fractal dimension, while showing promise, fails to consistently predict neural network generalization due to hyperparameter influence and adversarial initializations; prompting further research.

Meta-learning solves hybrid deep generative model unidentifiability!

ERM’s efficiency in feature learning surprisingly remains high even with massive feature maps; its excess risk asymptotically matches an oracle procedure’s, implying potential for streamlined feature-…

This paper tackles the ‘curse of horizon’ in off-policy evaluation for partially observable Markov decision processes (POMDPs) by proposing novel coverage assumptions, enabling polynomial estimation e…

New active learning algorithm, Adaptive-Weight Sampling (AWS), achieves faster convergence with theoretical guarantees, improving data efficiency for machine learning.

A novel algorithm, TIE, optimally teaches a family of linear behavior cloning learners, achieving instance-optimal teaching dimension while providing efficient approximation for larger action spaces.

Learning sparse functions efficiently with gradient methods is challenging; this paper introduces Differentiable Learning Queries (DLQ) to precisely characterize gradient query complexity, revealing s…

Two novel sampling strategies for spectral model sharding in federated learning minimize approximation error and create unbiased estimators, improving performance on various datasets.

Researchers enhanced Generative Flow Network training by introducing variance-reducing control variates for divergence-based learning objectives, accelerating convergence and improving accuracy.

This paper introduces novel autoregressive sampling and hybrid training strategies for score-based diffusion models, significantly boosting PDE forecasting and assimilation accuracy.

Improved unsupervised domain adaptation framework achieves superior performance via refined f-divergence and novel f-domain discrepancy, enabling faster algorithms and tighter generalization bounds.

Oja’s algorithm achieves minimax optimal error rates for streaming sparse PCA using a simple single-pass thresholding method, requiring only O(d) space and O(nd) time.

Offline RL agents often fail in real-world scenarios due to unseen test states. SCAS, a novel method, simultaneously corrects OOD states to high-value, in-distribution states and suppresses risky OOD …