Kai-Wei Chang, He He, Hal Daume III, John Langford, Stephane Ross

NIPS

Links

Abstract

Many machine learning applications involve jointly predicting multiple mutually dependent output variables. Learning to search is a family of methods where the complex decision problem is cast into a sequence of decisions via a search space. Although these methods have shown promise both in theory and in practice, implementing them has been burdensomely awkward. In this paper, we show the search space can be defined by an arbitrary imperative program, turning learning to search into a credit assignment compiler. Altogether with the algorithmic improvements for the compiler, we radically reduce the complexity of programming and the running time. We demonstrate the feasibility of our approach on multiple joint prediction tasks. In all cases, we obtain accuracies as high as alternative approaches, at drastically reduced execution and programming time.

Bib entry

@inproceedings{CHDLR16,
author = {Kai-Wei Chang and He He and Hal Daume III and John Langford and Stephane Ross},
title = {A Credit Assignment Compiler for Joint Prediction},
booktitle = {NIPS},
year = {2016},
}