Mixed-Integer Programming for Change-point Detection

TL;DR

This paper introduces a novel mixed-integer programming approach for offline multiple change-point detection, offering tighter relaxations and improved computational efficiency over existing methods, applicable to multidimensional and sparse change scenarios.

Contribution

The paper develops a family of strengthened MIP formulations with integral relaxations, enabling globally optimal change-point detection with faster solution times and extensions to complex data models.

Findings

Achieves tighter LP relaxations than previous formulations.

Reduces solution times on benchmark datasets.

Effective for multidimensional and sparse change-point detection.

Abstract

We present a new mixed-integer programming (MIP) approach for offline multiple change-point detection by casting the problem as a globally optimal piecewise linear (PWL) fitting problem. Our main contribution is a family of strengthened MIP formulations whose linear programming (LP) relaxations admit integral projections onto the segment assignment variables, which encode the segment membership of each data point. This property yields provably tighter relaxations than existing formulations for offline multiple change-point detection. We further extend the framework to two settings of active research interest: (i) multidimensional PWL models with shared change-points, and (ii) sparse change-point detection, where only a subset of dimensions undergo structural change. Extensive computational experiments on benchmark real-world datasets demonstrate that the proposed formulations achieve reductions in solution times under both $\ell_1$ and $\ell_2$ loss functions in comparison to the state-of-the-art.