On the Convergence of SARAH and Beyond

v1v2 (latest)

On the Convergence of SARAH and Beyond

International Conference on Artificial Intelligence and Statistics (AISTATS), 2019

5 June 2019

ArXiv (abs)PDF HTML

Papers citing "On the Convergence of SARAH and Beyond"

15 / 15 papers shown

Title
VASSO: Variance Suppression for Sharpness-Aware Minimization Bingcong Li Yilang Zhang G. Giannakis 216 1 0 02 Sep 2025
Convergence Analysis of the PAGE Stochastic Algorithm for Weakly Convex Finite-Sum Optimization Laurent Condat Peter Richtárik 84 0 0 31 Aug 2025
Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting Duc Toan Nguyen Trang H. Tran Lam M. Nguyen 101 0 0 14 Jun 2025
Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling Daniil Medyakov Gleb Molodtsov S. Chezhegov Alexey Rebrikov Aleksandr Beznosikov 357 1 0 21 Feb 2025
Enhancing Sharpness-Aware Optimization Through Variance SuppressionNeural Information Processing Systems (NeurIPS), 2023 Bingcong Li G. Giannakis AAML 336 32 0 27 Sep 2023
Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and AnalysisNeural Information Processing Systems (NeurIPS), 2023 Dachao Lin Yuze Han Haishan Ye Zhihua Zhang 287 13 0 15 Apr 2023
Gradient Descent-Type Methods: Background and Simple Unified Convergence Analysis Quoc Tran-Dinh Marten van Dijk 143 1 0 19 Dec 2022
Faster federated optimization under second-order similarityInternational Conference on Learning Representations (ICLR), 2022 Ahmed Khaled Chi Jin FedML 256 23 0 06 Sep 2022
Random-reshuffled SARAH does not need a full gradient computationsOptimization Letters (Optim. Lett.), 2021 Aleksandr Beznosikov Martin Takáč 217 11 0 26 Nov 2021
Practical Schemes for Finding Near-Stationary Points of Convex Finite-SumsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Kaiwen Zhou Lai Tian Anthony Man-Cho So James Cheng 176 10 0 25 May 2021
PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex OptimizationInternational Conference on Machine Learning (ICML), 2020 Zhize Li Hongyan Bao Xiangliang Zhang Peter Richtárik ODL 288 149 0 25 Aug 2020
Variance Reduction for Deep Q-Learning using Stochastic Recursive GradientInternational Conference on Neural Information Processing (ICONIP), 2020 Hao Jia Xiao Zhang Jun Xu Wei Zeng Hao Jiang Xiao Yan Ji-Rong Wen 150 3 0 25 Jul 2020
Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets Yanjie Dong G. Giannakis Tianyi Chen Julian Cheng Md. Jahangir Hossain Victor C. M. Leung FedML 125 14 0 17 Jun 2020
Adaptive Step Sizes in Variance Reduction via Regularization Bingcong Li G. Giannakis 114 5 0 15 Oct 2019
Almost Tune-Free Variance ReductionInternational Conference on Machine Learning (ICML), 2019 Bingcong Li Lingda Wang G. Giannakis 138 20 0 25 Aug 2019