Skip to yearly menu bar Skip to main content


Poster

The Physical Systems Behind Optimization Algorithms

Lin Yang · Raman Arora · Vladimir Braverman · Tuo Zhao

Room 210 #85

Keywords: [ Convex Optimization ] [ Non-Convex Optimization ] [ Control Theory ]


Abstract:

We use differential equations based approaches to provide some {\it \textbf{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 {\it \textbf{beyond}} convexity and strong convexity, e.g. Polyak-\L ojasiewicz and error bound conditions (possibly nonconvex).

Live content is unavailable. Log in and register to view live content