paper-with-me

홈 › Papers

Calibrating the Adaptive Learning Rate to Improve Convergence of ADAM

2019-08-02 · Qianqian Tong, Guannan Liang, Jinbo Bi

Adaptive gradient methods (AGMs) have become popular in optimizing the nonconvex problems in deep learning area. We revisit AGMs and identify that the adaptive learning rate (A-LR) used by AGMs varies significantly across the dimensions of the problem over epochs (i.e., anisotropic scale), which may lead to issues in convergence and generalization. All existing modified AGMs actually represent efforts in revising the A-LR. Theoretically, we provide a new way to analyze the convergence of AGMs and prove that the convergence rate of \textsc{Adam} also depends on its hyper-parameter $\epsilon$, which has been overlooked previously. Based on these two facts, we propose a new AGM by calibrating the A-LR with an activation ({\em softplus}) function, resulting in the \textsc{Sadam} and \textsc{SAMSGrad} methods \footnote{Code is available at https://github.com/neilliang90/Sadam.git.}. We further prove that these algorithms enjoy better convergence speed under nonconvex, non-strongly convex, and Polyak-{\L}ojasiewicz conditions compared with \textsc{Adam}. Empirical studies support our observation of the anisotropic A-LR and show that the proposed methods outperform existing AGMs and generalize even better than S-Momentum in multiple deep learning tasks.

📄 PDF Abstract BibTeX arXiv:1908.00700

Code (2)

neilliang90/Sadam 공식 구현 pytorch
lessw2020/Ranger-Deep-Learning-Optimizer pytorch

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Revealing Modular Gradient Noise Imbalance in LLMs: Calibrating Adam via Signal-to-Noise Ratio

2026-05-07 · Ziqing Wen, Zhouyang Liu, Jiahuan Wang, Ping Luo 외 arxiv

The impressive performance of large language models (LLMs) arises from their massive scale and heterogeneous module composition. However, this structural heterogeneity introduces additional optimization challenges. While…

AdaX: Adaptive Gradient Descent with Exponential Long Term Memory

2020-04-21 · Wenjie Li, Zhaoyang Zhang, Xinjiang Wang, Ping Luo

Although adaptive optimization algorithms such as Adam show fast convergence in many machine learning tasks, this paper identifies a problem of Adam by analyzing its performance in a simple non-convex synthetic problem, …

A Control Theoretic Framework for Adaptive Gradient Optimizers in Machine Learning

2022-06-04 · Kushal Chakrabarti, Nikhil Chopra

Adaptive gradient methods have become popular in optimizing deep neural networks; recent examples include AdaGrad and Adam. Although Adam usually converges faster, variations of Adam, for instance, the AdaBelief algorith…

BIG-bench Machine Learningimage-classificationImage ClassificationLanguage Modeling+1

An improvement of the convergence proof of the ADAM-Optimizer

2018-04-27 · Sebastian Bock, Josef Goppold, Martin Weiß

A common way to train neural networks is the Backpropagation. This algorithm includes a gradient descent method, which needs an adaptive step size. In the area of neural networks, the ADAM-Optimizer is one of the most po…

MaxVA: Fast Adaptation of Step Sizes by Maximizing Observed Variance of Gradients

2020-06-21 · Chen Zhu, Yu Cheng, Zhe Gan, Furong Huang 외

Adaptive gradient methods such as RMSProp and Adam use exponential moving estimate of the squared gradient to compute adaptive step sizes, achieving better convergence than SGD in face of noisy objectives. However, Adam …

Image ClassificationMachine TranslationNatural Language UnderstandingStochastic Optimization+1