Globalized Adversarial Regret Optimization: Robust Decisions with Uncalibrated Predictions

TL;DR

GARO is a novel decision framework that controls adversarial regret across all uncertainty set sizes, providing performance guarantees without probabilistic calibration, and improves robustness in uncertain optimization problems.

Contribution

Introduction of GARO, a new framework that controls adversarial regret uniformly, generalizes classical adaptation methods, and offers tractable reformulations with convergence guarantees.

Findings

GARO provides stronger global performance guarantees.

GARO achieves a better trade-off between worst-case and mean performance.

Experiments show GARO outperforms traditional methods in robustness.

Abstract

Optimization problems routinely depend on uncertain parameters that must be predicted before a decision is made. Classical robust and regret formulations are designed to handle erroneous predictions and can provide statistical error bounds in simple settings. However, when predictions lack rigorous error bounds (as is typical of modern machine learning methods) classical robust models often yield vacuous guarantees, while regret formulations can paradoxically produce decisions that are more optimistic than even a nominal solution. We introduce Globalized Adversarial Regret Optimization (GARO), a decision framework that controls adversarial regret, defined as the gap between the worst-case cost and the oracle robust cost, uniformly across all possible uncertainty set sizes. By design, GARO delivers absolute or relative performance guarantees against an oracle with full knowledge of the prediction error, without requiring any probabilistic calibration of the uncertainty set. We show that GARO equipped with a relative rate function generalizes the classical adaptation method of Lepski to downstream decision problems. We derive exact tractable reformulations for problems with affine worst-case cost functions and polyhedral norm uncertainty sets, and provide a discretization and a constraint-generation algorithm with convergence guarantees for general settings. Finally, experiments demonstrate that GARO yields solutions with a more favorable trade-off between worst-case and mean out-of-sample performance, as well as stronger global performance guarantees.