English

Potential-Function Proofs for First-Order Methods

Machine Learning 2019-06-04 v3 Data Structures and Algorithms Optimization and Control

Abstract

This note discusses proofs for convergence of first-order methods based on simple potential-function arguments. We cover methods like gradient descent (for both smooth and non-smooth settings), mirror descent, and some accelerated variants.

Keywords

Cite

@article{arxiv.1712.04581,
  title  = {Potential-Function Proofs for First-Order Methods},
  author = {Nikhil Bansal and Anupam Gupta},
  journal= {arXiv preprint arXiv:1712.04581},
  year   = {2019}
}