A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming

We propose a conditional gradient framework for a composite convex minimization template with broad applications. Our approach combines the notions of smoothing and homotopy under the CGM framework, and provably achieves the optimal O(1/sqrt(k)) convergence rate. We demonstrate that the same rate holds if the linear subproblems are solved approximately with additive or multiplicative error. Specific applications of the framework include the non-smooth minimization semidefinite programming, minimization with linear inclusion constraints over a compact domain. We provide numerical evidence to demonstrate the benefits of the new framework.


Published in:
Proceedings of the 35th International Conference on Machine Learning (ICML)
Presented at:
the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden, July 10-15, 2018
Year:
Jul 11 2018
Publisher:
Stockholm, ICML
Keywords:
Laboratories:




 Record created 2018-04-23, last modified 2019-03-17

Fulltext:
hcgm-infoscience - Download fulltextPDF
hcgm-icml2018 - Download fulltextPDF
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)