Stochastic Methods

ThoughtSculpt: Reasoning with Intermediate Revision and Search NAACL 2025 Towards Faster Decentralized Stochastic Optimization with Communication Compression ICLR 2025 Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory CVPR 2025 Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding EMNLP 2025 Tuning-Free Coreset Markov Chain Monte Carlo via Hot DoG UAI 2025 Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way AISTATS 2025 Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs AISTATS 2025 Understanding Silent Data Corruption in LLM Training ACL 2025 Zeroth-Order Methods for Nonconvex Stochastic Problems with Decision-Dependent Distributions AAAI 2025 A Bayesian Approach to Data Point Selection NeurIPS 2024 A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays NeurIPS 2024 A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems AAAI 2024 Accelerated Parameter-Free Stochastic Optimization COLT 2024 Accelerating Diffusion Sampling with Optimized Time Steps CVPR 2024 A Comparison of Continuous-Time Approximations to Stochastic Gradient Descent JMLR 2024 Adaptive Compression in Federated Learning via Side Information AISTATS 2024 Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions NeurIPS 2024 ADOPT: Modified Adam Can Converge with Any β_2 with the Optimal Rate NeurIPS 2024 Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness ICLR 2024 Almost Sure Convergence Rates Analysis and Saddle Avoidance of Stochastic Gradient Methods JMLR 2024 An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness NeurIPS 2024 An Analysis of Quantile Temporal-Difference Learning JMLR 2024 An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations NeurIPS 2024 An Online Bootstrap for Time Series AISTATS 2024 Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization ICLR 2024