The Physical Systems Behind Optimization Algorithms

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