Data-driven Algorithm Design

TL;DR

This paper surveys recent advances in data-driven combinatorial algorithm design, emphasizing methods that provide strong performance guarantees for both batch and online scenarios, addressing the challenge of parameter tuning in complex problems.

Contribution

It offers a comprehensive review of recent work that establishes computational and statistical guarantees for data-driven algorithm tuning in combinatorial problems.

Findings

Provides performance guarantees for data-driven algorithms

Addresses both batch and online problem scenarios

Highlights the impact of parameter tuning on algorithm performance

Abstract

Data driven algorithm design is an important aspect of modern data science and algorithm design. Rather than using off the shelf algorithms that only have worst case performance guarantees, practitioners often optimize over large families of parametrized algorithms and tune the parameters of these algorithms using a training set of problem instances from their domain to determine a configuration with high expected performance over future instances. However, most of this work comes with no performance guarantees. The challenge is that for many combinatorial problems of significant importance including partitioning, subset selection, and alignment problems, a small tweak to the parameters can cause a cascade of changes in the algorithm's behavior, so the algorithm's performance is a discontinuous function of its parameters. In this chapter, we survey recent work that helps put data-driven combinatorial algorithm design on firm foundations. We provide strong computational and statistical performance guarantees, both for the batch and online scenarios where a collection of typical problem instances from the given application are presented either all at once or in an online fashion, respectively.