Primal-Dual Block Frank-Wolfe
Machine Learning
2019-06-07 v1 Optimization and Control
Machine Learning
Abstract
We propose a variant of the Frank-Wolfe algorithm for solving a class of sparse/low-rank optimization problems. Our formulation includes Elastic Net, regularized SVMs and phase retrieval as special cases. The proposed Primal-Dual Block Frank-Wolfe algorithm reduces the per-iteration cost while maintaining linear convergence rate. The per iteration cost of our method depends on the structural complexity of the solution (i.e. sparsity/low-rank) instead of the ambient dimension. We empirically show that our algorithm outperforms the state-of-the-art methods on (multi-class) classification tasks.
Cite
@article{arxiv.1906.02436,
title = {Primal-Dual Block Frank-Wolfe},
author = {Qi Lei and Jiacheng Zhuo and Constantine Caramanis and Inderjit S. Dhillon and Alexandros G. Dimakis},
journal= {arXiv preprint arXiv:1906.02436},
year = {2019}
}