English

Approximate FW Algorithm with a novel DMO method over Graph-structured Support Set

Optimization and Control 2024-11-26 v2 Machine Learning

Abstract

In this project, we reviewed a paper that deals graph-structured convex optimization (GSCO) problem with the approximate Frank-Wolfe (FW) algorithm. We analyzed and implemented the original algorithm and introduced some extensions based on that. Then we conducted experiments to compare the results and concluded that our backtracking line-search method effectively reduced the number of iterations, while our new DMO method (Top-g+ optimal visiting) did not make satisfying enough improvements.

Keywords

Cite

@article{arxiv.2411.04389,
  title  = {Approximate FW Algorithm with a novel DMO method over Graph-structured Support Set},
  author = {Yijian Pan and Hongjiao Qiang},
  journal= {arXiv preprint arXiv:2411.04389},
  year   = {2024}
}