When Bits Break Recourse: Counterfactual-Faithful Quantization

2026-05-16

AI Summary

This work addresses the tension between low-bit quantization and algorithmic recourse, showing that aggressive quantization—while preserving predictive accuracy—can severely undermine counterfactual explainability by invalidating or drastically inflating the cost of recourse. The paper formally characterizes this trade-off through three criteria for counterfactual sensitivity: validity, cost, and directional stability, and introduces two novel metrics, Validity Drop (VD) and Counterfactual Recourse Gap (CRG), to quantify recourse degradation. To reconcile efficiency with explainability, the authors propose Counterfactually Faithful Quantization (CFQ), a method that jointly optimizes prediction accuracy and recourse fidelity under a global bit budget via teacher-guided target constraints, mixed-precision bit allocation, and boundary perturbation theory. Experiments on Adult, German Credit, and COMPAS datasets demonstrate that CFQ significantly outperforms baselines, achieving comparable accuracy while markedly improving both VD and CRG.

Abstract

Quantization can preserve predictive accuracy under low-bit deployment while silently breaking algorithmic recourse: an actionable change that flips a decision before quantization may fail after quantization, or become substantially more costly. We formalize counterfactual sensitivity under quantization through validity, cost, and direction stability, and introduce two metrics: Validity Drop (VD) and Counterfactual Recourse Gap (CRG) that reveal recourse failures invisible to accuracy. We propose Counterfactual-Faithful Quantization (CFQ), which trains quantizer parameters and mixed-precision bit allocation to preserve counterfactual behavior by enforcing the target outcome at teacher recourse points under a global bit budget. A margin-based analysis gives a sufficient condition for recourse transfer under bounded quantization perturbations. Experiments on Adult, German Credit, and COMPAS show that accuracy-matched baselines can significantly degrade recourse stability, while CFQ maintains accuracy and substantially improves VD and CRG across bit budgets.

Problem

• quantization
• algorithmic recourse
• counterfactual
• low-bit deployment
• recourse stability

Innovation

• Counterfactual Recourse
• Quantization
• Mixed-Precision
• Algorithmic Fairness
• Validity Drop