One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

27 May 2019

Papers citing "One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods"

9 / 9 papers shown

Title
LoCoDL: Communication-Efficient Distributed Learning with Local Training and Compression Laurent Condat Artavazd Maranjyan Peter Richtárik 54 4 0 07 Mar 2024
GradSkip: Communication-Accelerated Local Gradient Methods with Better Computational Complexity Artavazd Maranjyan M. Safaryan Peter Richtárik 39 13 0 28 Oct 2022
Local SGD: Unified Theory and New Efficient Methods Eduard A. Gorbunov Filip Hanzely Peter Richtárik FedML 37 109 0 03 Nov 2020
Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters Filip Hanzely 42 0 0 26 Aug 2020
Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization Zhize Li D. Kovalev Xun Qian Peter Richtárik FedML AI4CE 29 135 0 26 Feb 2020
Adaptivity of Stochastic Gradient Methods for Nonconvex Optimization Samuel Horváth Lihua Lei Peter Richtárik Michael I. Jordan 57 30 0 13 Feb 2020
Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems Filip Hanzely D. Kovalev Peter Richtárik 40 17 0 11 Feb 2020
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark Schmidt 139 1,205 0 16 Aug 2016
A Proximal Stochastic Gradient Method with Progressive Variance Reduction Lin Xiao Tong Zhang ODL 93 737 0 19 Mar 2014