paper-with-me

Papers

AdaPlus: Integrating Nesterov Momentum and Precise Stepsize Adjustment on AdamW Basis

2023-09-05 · Lei Guan

This paper proposes an efficient optimizer called AdaPlus which integrates Nesterov momentum and precise stepsize adjustment on AdamW basis. AdaPlus combines the advantages of AdamW, Nadam, and AdaBelief and, in particular, does not introduce any extra hyper-parameters. We perform extensive experimental evaluations on three machine learning tasks to validate the effectiveness of AdaPlus. The experiment results validate that AdaPlus (i) among all the evaluated adaptive methods, performs most comparable with (even slightly better than) SGD with momentum on image classification tasks and (ii) outperforms other state-of-the-art optimizers on language modeling tasks and illustrates pretty high stability when training GANs. The experiment code of AdaPlus will be accessible at: https://github.com/guanleics/AdaPlus.

📄 PDF Abstract BibTeX arXiv:2309.01966

Code (1)

guanleics/adaplus 공식 구현 pytorch

Tasks

image-classificationImage ClassificationLanguage ModelingLanguage Modelling

Methods 이 논문이 사용한 방법론

Adabelief 설명 없음
SGD with Momentum 설명 없음
AdamW AdamW is a stochastic optimization method that modifies the typical implementation of weight decay in Adam, by decoupling [weight…
SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Convergence of Gradient Algorithms for Nonconvex C^{1+alpha} Cost Functions

2020-12-01 · Zixuan Wang, Shanjian Tang

This paper is concerned with convergence of stochastic gradient algorithms with momentum terms in the nonconvex setting. A class of stochastic momentum methods, including stochastic gradient descent, heavy ball, and Nest…

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent

2025-02-16 · Ya-Chi Chu, Wenzhi Gao, Yinyu Ye, Madeleine Udell

This paper investigates the convergence properties of the hypergradient descent method (HDM), a 25-year-old heuristic originally proposed for adaptive stepsize selection in stochastic first-order methods. We provide the …

Amortized Nesterov's Momentum: Robust and Lightweight Momentum for Deep Learning

2019-09-25 · Kaiwen Zhou, Yanghua Jin, Qinghua Ding, James Cheng

Stochastic Gradient Descent (SGD) with Nesterov's momentum is a widely used optimizer in deep learning, which is observed to have excellent generalization performance. However, due to the large stochasticity, SGD with Ne…

Deep Learning

ADA+: A GENERIC FRAMEWORK WITH MORE ADAPTIVE EXPLICIT ADJUSTMENT FOR LEARNING RATE

2019-09-25 · Yue Zhao, Xiangsheng Huang, Ludan Kou

Although adaptive algorithms have achieved significant success in training deep neural networks with faster training speed, they tend to have poor generalization performance compared to SGD with Momentum(SGDM). One of th…

Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent

2016-07-07 · Aleksandar Botev, Guy Lever, David Barber

We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov's accelerated gradient method, len…