English

A Variational Perspective on High-Resolution ODEs

Optimization and Control 2023-11-06 v1 Machine Learning Numerical Analysis Numerical Analysis

Abstract

We consider unconstrained minimization of smooth convex functions. We propose a novel variational perspective using forced Euler-Lagrange equation that allows for studying high-resolution ODEs. Through this, we obtain a faster convergence rate for gradient norm minimization using Nesterov's accelerated gradient method. Additionally, we show that Nesterov's method can be interpreted as a rate-matching discretization of an appropriately chosen high-resolution ODE. Finally, using the results from the new variational perspective, we propose a stochastic method for noisy gradients. Several numerical experiments compare and illustrate our stochastic algorithm with state of the art methods.

Keywords

Cite

@article{arxiv.2311.02002,
  title  = {A Variational Perspective on High-Resolution ODEs},
  author = {Hoomaan Maskan and Konstantinos C. Zygalakis and Alp Yurtsever},
  journal= {arXiv preprint arXiv:2311.02002},
  year   = {2023}
}

Comments

37th Annual Conference on Neural Information Processing Systems (NeurIPS 2023)

R2 v1 2026-06-28T13:10:49.293Z