SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance

17 February 2023

Papers citing "SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance"

10 / 10 papers shown

Title
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions Yusu Hong Junhong Lin 91 13 0 06 Feb 2024
Making SGD Parameter-Free Y. Carmon Oliver Hinder 63 45 0 04 May 2022
High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize Ali Kavis Kfir Y. Levy Volkan Cevher 50 40 0 06 Apr 2022
The Power of Adaptivity in SGD: Self-Tuning Step Sizes with Unbounded Gradients and Affine Variance Matthew Faw Isidoros Tziotis Constantine Caramanis Aryan Mokhtari Sanjay Shakkottai Rachel A. Ward 53 59 0 11 Feb 2022
A new regret analysis for Adam-type algorithms Ahmet Alacaoglu Yura Malitsky P. Mertikopoulos Volkan Cevher ODL 53 41 0 21 Mar 2020
Lipschitz and Comparator-Norm Adaptivity in Online Learning Zakaria Mhammedi Wouter M. Koolen 61 56 0 27 Feb 2020
On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization Dongruo Zhou Yiqi Tang Yuan Cao Ziyan Yang Quanquan Gu 52 151 0 16 Aug 2018
On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes Xiaoyun Li Francesco Orabona 67 295 0 21 May 2018
Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming Saeed Ghadimi Guanghui Lan ODL 120 1,548 0 22 Sep 2013
No More Pesky Learning Rates Tom Schaul Sixin Zhang Yann LeCun 123 478 0 06 Jun 2012