English

Lazifying Conditional Gradient Algorithms

Data Structures and Algorithms 2018-09-06 v4 Machine Learning

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.

Cite

@article{arxiv.1610.05120,
  title  = {Lazifying Conditional Gradient Algorithms},
  author = {Gábor Braun and Sebastian Pokutta and Daniel Zink},
  journal= {arXiv preprint arXiv:1610.05120},
  year   = {2018}
}

Comments

25 pages and 31 pages of computational results

R2 v1 2026-06-22T16:22:54.305Z