Abstract | ||
---|---|---|
We use differential equations based approaches to provide some physics insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton's methods as well as their Nesterov's accelerated variants in a unified framework motivated by a natural connection of optimization algorithms to physical systems. Our analysis is applicable to more general algorithms and optimization problems beyond convexity and strong convexity, e.g. Polyak-Lojasiewicz and error bound conditions (possibly nonconvex). |
Year | Venue | Keywords |
---|---|---|
2018 | ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018) | unified framework,physical systems,strong convexity,optimization problems,gradient descent,machine learning,ordinary differential equation |
DocType | Volume | ISSN |
Conference | 31 | 1049-5258 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Yang | 1 | 31 | 21.21 |
R. Arora | 2 | 489 | 35.97 |
Vladimir Braverman | 3 | 357 | 34.36 |
Tuo Zhao | 4 | 222 | 40.58 |