Utilitarian Algorithm Configuration for Infinite Parameter Spaces

TL;DR

This paper introduces COUP, a new algorithm configuration method capable of efficiently searching infinite parameter spaces, maintaining theoretical guarantees, and outperforming previous finite-space methods.

Contribution

The paper presents COUP, a novel procedure that extends utilitarian algorithm configuration to infinite parameter spaces with proven efficiency and effectiveness.

Findings

COUP effectively searches infinite parameter spaces.

COUP maintains theoretical guarantees of previous methods.

COUP outperforms existing approaches in experiments.

Abstract

Utilitarian algorithm configuration is a general-purpose technique for automatically searching the parameter space of a given algorithm to optimize its performance, as measured by a given utility function, on a given set of inputs. Recently introduced utilitarian configuration procedures offer optimality guarantees about the returned parameterization while provably adapting to the hardness of the underlying problem. However, the applicability of these approaches is severely limited by the fact that they only search a finite, relatively small set of parameters. They cannot effectively search the configuration space of algorithms with continuous or uncountable parameters. In this paper we introduce a new procedure, which we dub COUP (Continuous, Optimistic Utilitarian Procrastination). COUP is designed to search infinite parameter spaces efficiently to find good configurations quickly. Furthermore, COUP maintains the theoretical benefits of previous utilitarian configuration procedures when applied to finite parameter spaces but is significantly faster, both provably and experimentally.