Learning Predictions for Algorithms with Predictions

TL;DR

This paper introduces a general framework for designing algorithms that learn predictors to improve performance in online problems, demonstrating its effectiveness across multiple classic problems with improved or novel guarantees.

Contribution

The paper presents a unified approach for integrating learning into algorithms with predictions, including analysis of performance dependence on prediction quality and sample complexity bounds.

Findings

Improved results for bipartite matching, ski-rental, page migration, and job scheduling.

Simpler analysis compared to previous methods.

First learning-theoretic guarantees for some problems.

Abstract

A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem. While much work has focused on using predictions to improve competitive ratios, running times, or other performance measures, less effort has been devoted to the question of how to obtain the predictions themselves, especially in the critical online setting. We introduce a general design approach for algorithms that learn predictors: (1) identify a functional dependence of the performance measure on the prediction quality and (2) apply techniques from online learning to learn predictors, tune robustness-consistency trade-offs, and bound the sample complexity. We demonstrate the effectiveness of our approach by applying it to bipartite matching, ski-rental, page migration, and job scheduling. In several settings we improve upon multiple existing results while utilizing a much simpler analysis, while in the others we provide the first learning-theoretic guarantees.