Random-reshuffled SARAH does not need a full gradient computations

26 November 2021

Papers citing "Random-reshuffled SARAH does not need a full gradient computations"

8 / 8 papers shown

Title
Variance Reduction Methods Do Not Need to Compute Full Gradients: Improved Efficiency through Shuffling Daniil Medyakov Gleb Molodtsov S. Chezhegov Alexey Rebrikov Aleksandr Beznosikov 103 0 0 21 Feb 2025
Stochastic optimization with arbitrary recurrent data sampling William G. Powell Hanbaek Lyu 37 0 0 15 Jan 2024
Federated Learning with Regularized Client Participation Grigory Malinovsky Samuel Horváth Konstantin Burlachenko Peter Richtárik FedML 31 13 0 07 Feb 2023
Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning Kazusato Oko Shunta Akiyama Tomoya Murata Taiji Suzuki FedML 41 0 0 01 Sep 2022
On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms Lam M. Nguyen Trang H. Tran 32 2 0 13 Jun 2022
New Convergence Aspects of Stochastic Gradient Algorithms Lam M. Nguyen Phuong Ha Nguyen Peter Richtárik K. Scheinberg Martin Takáč Marten van Dijk 23 66 0 10 Nov 2018
Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate Aryan Mokhtari Mert Gurbuzbalaban Alejandro Ribeiro 27 36 0 01 Nov 2016
Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learning Julien Mairal 79 317 0 18 Feb 2014