Adaptive learning rate method based on Nesterov accelerated gradient

Zhenxing Xu; Ping Yang; Bing Xu; Heping Li

doi:10.1117/12.2284928

24 October 2017 Adaptive learning rate method based on Nesterov accelerated gradient

Zhenxing Xu, Ping Yang, Bing Xu, Heping Li

Proceedings Volume 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications; 104622R (2017) https://doi.org/10.1117/12.2284928
Event: Applied Optics and Photonics China (AOPC2017), 2017, Beijing, China

Abstract

A kind of stochastic gradient descent method of self-adaptive learning rate is proposed in this thesis. This method is based on the optimization algorithm Nesterov accelerated gradient (NAG). First second derivative approximation of cost function is executed, then the final update orientation is corrected through self-adaptive learning rate, and the convergence of the method is analyzed theoretically. This method required no manual adjustment of the learning rate and is robust in the selection of noise gradient information and hyper-parameters, featuring high computation efficiency and small memory overhead. Finally, a comparison is made between this method and other stochastic gradient descent methods through MNIST digital classification task, and the experiment result showed that Adan worked well with the faster rate of convergence and is better than other stochastic gradient descent optimization methods.

Citation Download Citation

Zhenxing Xu, Ping Yang, Bing Xu, and Heping Li "Adaptive learning rate method based on Nesterov accelerated gradient", Proc. SPIE 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications, 104622R (24 October 2017); https://doi.org/10.1117/12.2284928

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available