Adaptive Stochastic Dual Coordinate Ascent for Conditional Random Fields

TL;DR

This paper adapts the stochastic dual coordinate ascent algorithm to efficiently train conditional random fields, demonstrating competitive performance and improvements on sequence prediction tasks, especially with sparse features.

Contribution

It introduces an adaptive SDCA method for CRFs, incorporating non-uniform sampling based on duality gaps, which was not previously applied to CRF training.

Findings

SDCA achieves performance comparable to state-of-the-art methods.

SDCA outperforms existing methods on three of four datasets with sparse features.

The approach benefits from an exact line search with a single marginalization oracle call.

Abstract

This work investigates the training of conditional random fields (CRFs) via the stochastic dual coordinate ascent (SDCA) algorithm of Shalev-Shwartz and Zhang (2016). SDCA enjoys a linear convergence rate and a strong empirical performance for binary classification problems. However, it has never been used to train CRFs. Yet it benefits from an `exact' line search with a single marginalization oracle call, unlike previous approaches. In this paper, we adapt SDCA to train CRFs, and we enhance it with an adaptive non-uniform sampling strategy based on block duality gaps. We perform experiments on four standard sequence prediction tasks. SDCA demonstrates performances on par with the state of the art, and improves over it on three of the four datasets, which have in common the use of sparse features.