DeepAI AI Chat
Log In Sign Up

Adaptive Gradient Methods with Dynamic Bound of Learning Rate

by   Liangchen Luo, et al.
University of Southern California
Zhejiang University
Peking University

Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of Adam and AMSGrad, called AdaBound and AMSBound respectively, which employ dynamic bounds on learning rates to achieve a gradual and smooth transition from adaptive methods to SGD and give a theoretical proof of convergence. We further conduct experiments on various popular tasks and models, which is often insufficient in previous work. Experimental results show that new variants can eliminate the generalization gap between adaptive methods and SGD and maintain higher learning speed early in training at the same time. Moreover, they can bring significant improvement over their prototypes, especially on complex deep networks. The implementation of the algorithm can be found at .


page 1

page 2

page 3

page 4


An Adaptive and Momental Bound Method for Stochastic Learning

Training deep neural networks requires intricate initialization and care...

A New Adaptive Gradient Method with Gradient Decomposition

Adaptive gradient methods, especially Adam-type methods (such as Adam, A...

EAdam Optimizer: How ε Impact Adam

Many adaptive optimization methods have been proposed and used in deep l...

On the Convergence of AdaBound and its Connection to SGD

Adaptive gradient methods such as Adam have gained extreme popularity du...

Adaptively Preconditioned Stochastic Gradient Langevin Dynamics

Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise t...

AdaL: Adaptive Gradient Transformation Contributes to Convergences and Generalizations

Adaptive optimization methods have been widely used in deep learning. Th...

Improving Layer-wise Adaptive Rate Methods using Trust Ratio Clipping

Training neural networks with large batch is of fundamental significance...

Code Repositories


An optimizer that trains as fast as Adam and as good as SGD.

view repo