Semi-Stochastic Frank-Wolfe Algorithms with Away-Steps for Block-Coordinate Structure Problems

Abstract

We propose a semi-stochastic Frank-Wolfe algorithm with away-steps for regularized empirical risk minimization and extend it to problems with block-coordinate structure. Our algorithms use adaptive step-size and we show that they converge linearly in expectation. The proposed algorithms can be applied to many important problems in statistics and machine learning including regularized generalized linear models, support vector machines and many others. In preliminary numerical tests on structural SVM and graph-guided fused LASSO, our algorithms outperform other competing algorithms in both iteration cost and total number of data passes.

References in corpus (5)

• Faster Rates for the Frank-Wolfe Method over Strongly-Convex Sets
• The Complexity of Large-scale Convex Programming under a Linear Optimization Oracle
• Smoothing Proximal Gradient Method for General Structured Sparse Learning
• Scalable Robust Matrix Recovery: Frank-Wolfe Meets Proximal Methods
• An Affine Invariant Linear Convergence Analysis for Frank-Wolfe Algorithms