Learning-Augmented Robust Algorithmic Recourse

TL;DR

This paper introduces a learning-augmented framework for algorithmic recourse, aiming to reduce costs by leveraging future model predictions while balancing robustness and consistency.

Contribution

It proposes a novel algorithm that utilizes predictions of future models to optimize recourse costs, analyzing the trade-off between robustness and consistency.

Findings

The proposed algorithm effectively reduces recourse costs with accurate predictions.

Prediction accuracy significantly influences the balance between robustness and cost.

The study characterizes the robustness-consistency trade-off in learning-augmented recourse.

Abstract

Algorithmic recourse provides individuals who receive undesirable outcomes from machine learning systems with minimum-cost improvements to achieve a desirable outcome. However, machine learning models often get updated, so the recourse may not lead to the desired outcome. The robust recourse framework chooses recourses that are less sensitive to adversarial model changes, but this comes at a higher cost. To address this, we initiate the study of learning-augmented algorithmic recourse and evaluate the extent to which a designer equipped with a prediction of the future model can reduce the cost of recourse when the prediction is accurate (consistency) while also limiting the cost even when the prediction is inaccurate (robustness). We propose a novel algorithm, study the robustness-consistency trade-off, and analyze how prediction accuracy affects performance.