Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs

Abstract : In this paper, we propose several improvements on the block-coordinate Frank-Wolfe (BCFW) algorithm from Lacoste-Julien et al. (2013) recently used to optimize the structured support vector machine (SSVM) objective in the context of structured prediction, though it has wider applications. The key intuition behind our improvements is that the estimates of block gaps maintained by BCFW reveal the block suboptimality that can be used as an adaptive criterion. First, we sample objects at each iteration of BCFW in an adaptive non-uniform way via gapbased sampling. Second, we incorporate pairwise and away-step variants of Frank-Wolfe into the block-coordinate setting. Third, we cache oracle calls with a cache-hit criterion based on the block gaps. Fourth, we provide the first method to compute an approximate regularization path for SSVM. Finally, we provide an exhaustive empirical evaluation of all our methods on four structured prediction datasets.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01323727
Contributor : Jean-Baptiste Alayrac <>
Submitted on : Tuesday, May 31, 2016 - 10:10:09 AM
Last modification on : Tuesday, February 5, 2019 - 1:52:14 PM

Links full text

Identifiers

  • HAL Id : hal-01323727, version 1
  • ARXIV : 1605.09346

Citation

Anton Osokin, Jean-Baptiste Alayrac, Isabella Lukasewitz, Puneet K. Dokania, Simon Lacoste-Julien. Minding the Gaps for Block Frank-Wolfe Optimization of Structured SVMs. International Conference on Machine Learning (ICML 2016)., 2016, New York, United States. ⟨hal-01323727⟩

Share

Metrics

Record views

582