Frank-Wolfe variants for minimization of a sum of functions

Abstract

We propose several variants of the Frank-Wolfe algorithm to minimize a sum of functions. The main proposed algorithm is inspired from the dual averaging scheme of Nesterov adapted for Frank Wolfe in a stochastic setting. A distributed version of this scheme is also suggested. Additionally, we propose a Frank-Wolfe variant based on incremental gradient techniques. The convergence rates for all the proposed algorithms are established. The performance is studied on least squares regression and multinomial classification.

False claim made in one of the theorems

References in corpus (3)

• Block-Coordinate Frank-Wolfe Optimization for Structural SVMs
• Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets
• The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle