Stochastic Frank-Wolfe Methods for Nonconvex Optimization

Understand

We study Frank-Wolfe methods for nonconvex stochastic and finite-sum optimization problems.

• Frank-Wolfe methods (in the convex case) have gained tremendous recent interest in machine learning and optimization communities due to their projection-free property and their ability to exploit structured constraints.
• However, our understanding of these algorithms in the nonconvex setting is fairly limited.
• In this paper, we propose nonconvex stochastic Frank-Wolfe methods and analyze their convergence properties.