An Efficient Fisher Matrix Approximation Method for Large-Scale Neural Network Optimization-Reference-Cited by-同舟云学术

An Efficient Fisher Matrix Approximation Method for Large-Scale Neural Network Optimization

Author:

Yang Minghan¹,Xu Dong²,Cui Qiwen³,Wen Zaiwen⁴^ORCID,Xu Pengxiang⁵

Affiliation:

1. DAMO Academy, Alibaba Group, China

2. Beijing International Center for Mathematical Research, Peking University, China

3. Paul G. Allen School of Computer Science & Engineering, University of Washington, USA

4. Beijing International Center for Mathematical Research, College of Engineering and Center for Machine Learning Research, Peking University, China

5. Peng Cheng Laboratory, China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference33 articles.

1. Topmoumoute online natural gradient algorithm;roux;Proc Adv Neural Inf Process Syst,2008

2. New insights and perspectives on the natural gradient method;martens;J Mach Learn Res,2020

3. Optimizing neural networks with kronecker-factored approximate curvature;martens;Proc Int Conf Mach Learn,2015

5. Quantum chemistry structures and properties of 134 kilo molecules;ramakrishnan;Data Science Journal,2014

Cited by 2 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Riemannian Natural Gradient Methods;SIAM Journal on Scientific Computing;2024-01-22