paper-with-me

홈 › Papers

Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance

2024-04-01 · Qi Zhang, Yi Zhou, Shaofeng Zou

This paper provides the first tight convergence analyses for RMSProp and Adam in non-convex optimization under the most relaxed assumptions of coordinate-wise generalized smoothness and affine noise variance. We first analyze RMSProp, which is a special case of Adam with adaptive learning rates but without first-order momentum. Specifically, to solve the challenges due to dependence among adaptive update, unbounded gradient estimate and Lipschitz constant, we demonstrate that the first-order term in the descent lemma converges and its denominator is upper bounded by a function of gradient norm. Based on this result, we show that RMSProp with proper hyperparameters converges to an $\epsilon$-stationary point with an iteration complexity of $\mathcal O(\epsilon^{-4})$. We then generalize our analysis to Adam, where the additional challenge is due to a mismatch between the gradient and first-order momentum. We develop a new upper bound on the first-order term in the descent lemma, which is also a function of the gradient norm. We show that Adam with proper hyperparameters converges to an $\epsilon$-stationary point with an iteration complexity of $\mathcal O(\epsilon^{-4})$. Our complexity results for both RMSProp and Adam match with the complexity lower bound established in \cite{arjevani2023lower}.

📄 PDF Abstract BibTeX arXiv:2404.01436

Code (0)

등록된 구현이 없습니다.

Tasks

LEMMA

Methods 이 논문이 사용한 방법론

RMSProp RMSProp is an unpublished adaptive learning rate optimizer proposed by Geoff Hinton. The motivation…
Adam 설명 없음

Similar Papers 제목 키워드 기반

Convergence of Steepest Descent and Adam under Non-Uniform Smoothness

2026-05-28 · Sharan Vaswani, Yifan Sun, Reza Babanezhad arxiv

Recent work has analyzed the convergence of first-order methods under non-uniform smoothness assumptions that better model the loss landscape in machine learning tasks. We generalize this assumption to objectives whose c…

Reinforcement Learning

Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration

2018-07-18 · ICLR 2019 5 · Soham De, Anirbit Mukherjee, Enayat Ullah

RMSProp and ADAM continue to be extremely popular algorithms for training neural nets but their theoretical convergence properties have remained unclear. Further, recent work has seemed to suggest that these algorithms h…

A Sufficient Condition for Convergences of Adam and RMSProp

2018-11-23 · CVPR 2019 6 · Fangyu Zou, Li Shen, Zequn Jie, Weizhong Zhang 외

Adam and RMSProp are two of the most influential adaptive stochastic algorithms for training deep neural networks, which have been pointed out to be divergent even in the convex setting via a few simple counterexamples. …

Stochastic Optimization

Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks

2016-11-07 · ICML 2017 8 · David Balduzzi, Brian McWilliams, Tony Butler-Yeoman

Modern convolutional networks, incorporating rectifiers and max-pooling, are neither smooth nor convex; standard guarantees therefore do not apply. Nevertheless, methods from convex optimization such as gradient descent …

A decreasing scaling transition scheme from Adam to SGD

2021-06-12 · Kun Zeng, Jinlan Liu, Zhixia Jiang, Dongpo Xu

Adaptive gradient algorithm (AdaGrad) and its variants, such as RMSProp, Adam, AMSGrad, etc, have been widely used in deep learning. Although these algorithms are faster in the early phase of training, their generalizati…