Momentum Improves Normalized SGD

9 February 2020

Papers citing "Momentum Improves Normalized SGD"

25 / 25 papers shown

Title
Understanding Gradient Orthogonalization for Deep Learning via Non-Euclidean Trust-Region Optimization Dmitry Kovalev 57 0 0 16 Mar 2025
Spectral-factorized Positive-definite Curvature Learning for NN Training Wu Lin Felix Dangel Runa Eschenhagen Juhan Bae Richard E. Turner Roger B. Grosse 47 0 0 10 Feb 2025
Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees Aleksandar Armacki Shuhua Yu Pranay Sharma Gauri Joshi Dragana Bajović D. Jakovetić S. Kar 57 2 0 17 Oct 2024
From Gradient Clipping to Normalization for Heavy Tailed SGD Florian Hübler Ilyas Fatkhullin Niao He 40 5 0 17 Oct 2024
Gradient-Free Method for Heavily Constrained Nonconvex Optimization Wanli Shi Hongchang Gao Bin Gu 21 5 0 31 Aug 2024
Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum H. Cai Sulaiman A. Alghunaim Ali H.Sayed 52 1 0 18 Jun 2024
Does SGD really happen in tiny subspaces? Minhak Song Kwangjun Ahn Chulhee Yun 73 5 1 25 May 2024
Random Scaling and Momentum for Non-smooth Non-convex Optimization Qinzi Zhang Ashok Cutkosky 43 4 0 16 May 2024
Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs Swetha Ganesh Washim Uddin Mondal Vaneet Aggarwal 49 3 0 02 Apr 2024
Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance Qi Zhang Yi Zhou Shaofeng Zou 42 4 0 01 Apr 2024
Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks Hristo Papazov Scott Pesme Nicolas Flammarion 38 5 0 08 Mar 2024
Non-Convex Stochastic Composite Optimization with Polyak Momentum Yuan Gao Anton Rodomanov Sebastian U. Stich 39 6 0 05 Mar 2024
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis Jie Hao Xiaochuan Gong Mingrui Liu 33 7 0 17 Jan 2024
SING: A Plug-and-Play DNN Learning Technique Adrien Courtois Damien Scieur Jean-Michel Morel Pablo Arias Thomas Eboli 36 0 0 25 May 2023
On the Optimal Batch Size for Byzantine-Robust Distributed Learning Yi-Rui Yang Chang-Wei Shi Wu-Jun Li FedML AAML 27 0 0 23 May 2023
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods Junchi Yang Xiang Li Ilyas Fatkhullin Niao He 42 15 0 21 May 2023
A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization Ashwinee Panda Xinyu Tang Saeed Mahloujifar Vikash Sehwag Prateek Mittal 43 11 0 08 Dec 2022
Momentum Aggregation for Private Non-convex ERM Hoang Tran Ashok Cutkosky 26 14 0 12 Oct 2022
Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger Zhiqi Bu Yu-Xiang Wang Sheng Zha George Karypis 27 69 0 14 Jun 2022
A Novel Convergence Analysis for Algorithms of the Adam Family Zhishuai Guo Yi Tian Xu W. Yin Rong Jin Tianbao Yang 39 47 0 07 Dec 2021
AGGLIO: Global Optimization for Locally Convex Functions Debojyoti Dey B. Mukhoty Purushottam Kar 14 2 0 06 Nov 2021
Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis Jikai Jin Samir Bhatt Haiyang Wang Liwei Wang 32 47 0 24 Oct 2021
ErrorCompensatedX: error compensation for variance reduced algorithms Hanlin Tang Yao Li Ji Liu Ming Yan 32 9 0 04 Aug 2021
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness Vien V. Mai M. Johansson 31 38 0 12 Feb 2021
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations Yossi Arjevani Y. Carmon John C. Duchi Dylan J. Foster Ayush Sekhari Karthik Sridharan 87 53 0 24 Jun 2020