Lazifying Conditional Gradient Algorithms

[edit]

Gábor Braun, Sebastian Pokutta, Daniel Zink ;
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:566-575, 2017.

Abstract

Conditional gradient algorithms (also often called Frank-Wolfe algorithms) are popular due to their simplicity of only requiring a linear optimization oracle and more recently they also gained significant traction for online learning. While simple in principle, in many cases the actual implementation of the linear optimization oracle is costly. We show a general method to lazify various conditional gradient algorithms, which in actual computations leads to several orders of magnitude of speedup in wall-clock time. This is achieved by using a faster separation oracle instead of a linear optimization oracle, relying only on few linear optimization oracle calls.

Related Material