When Bits Break Recourse: Counterfactual-Faithful Quantization

• URL: http://arxiv.org/abs/2605.17160v1
• Date: Sat, 16 May 2026 21:19:31 GMT
• Title: When Bits Break Recourse: Counterfactual-Faithful Quantization
• Abstract summary: We formalize counterfactual sensitivity under quantization through validity, cost, and direction stability.<n>We propose Counterfactual-Faithful Quantization (CFQ), which trains quantizer parameters and mixed-precision bit allocation to preserve counterfactual behavior.
• Score: 0.6999740786886536
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Quantization-Triggered Backdoors in Language Models: Cross-Quantizer Transferability and the Validation--Deployment Gap [0.0]
  Post-training quantization is often treated as a semantically neutral optimization for edge deployment of Large Language Models.<n>We show that backdoored translation models move from zero measured friend--foe corruption at repaired FP16 to up to 85.02% inversion after quantization.<n>We formalize this gap through Quantization Behavioral Equivalence Classes (QBECs) and prove that QBEC membership does not imply behavioral equivalence.
  arXiv  Detail & Related papers  (2026-08-27T08:34:10Z)
• Decision Kernels for Quantum Error Mitigation: Why Accuracy Gains Need Not Improve Downstream Decisions [0.0]
  We develop a theory of finite-shot QEM for downstream decisions.<n>We prove quotient factorization, gap-law minimality, a marginal no-go theorem, a QEM pullback theorem, and a fixed-allocation shot-level converse.
  arXiv  Detail & Related papers  (2026-07-03T02:35:57Z)
• Proper Scoring Rules for Agentic Uncertainty Quantification [0.038379177968040606]
  Trajectory Proper Score (TPS) is a predictor-agnostic family of strictly proper trajectory-level scoring rules.<n>Trajectory ECE is resolution-blind, while scalarized Trajectory Brier elicits only the collapsed scalar, not the full trace.
  arXiv  Detail & Related papers  (2026-05-23T22:22:00Z)
• Amortized-Precision Quantization for Early-Exit Vision Transformers [14.001192614503807]
  We introduce Amortized-Precision Quantization (APQ), a utilization-aware formulation that accounts for layer-wise exposure to quantization noise.<n>We propose Mutual Adaptive Quantization with Early Exiting (MAQEE), a bi-level framework that jointly optimize exit thresholds and bit-widths under explicit risk control to improve inference stability.
  arXiv  Detail & Related papers  (2026-05-08T06:27:04Z)
• Distill-Belief: Closed-Loop Inverse Source Localization and Characterization in Physical Fields [19.32007397161956]
  We propose textbfDistill-Belief, a teacher-student framework that decouples correctness from efficiency.<n>Experiments show that Distill-Belief consistently reduces sensing cost and improves success, posterior contraction, and estimation accuracy over baselines.
  arXiv  Detail & Related papers  (2026-04-28T20:18:29Z)
• Quantization of Spiking Neural Networks Beyond Accuracy [3.43677310385818]
  We show that firing activity governs effective sparsity, state storage, and event-processing load in SNNs.<n>We propose Earth Mover's Distance as a diagnostic metric for firing distribution divergence.<n>We find that uniform quantization induces distributional drift even when accuracy is preserved, while LQ-Net style learned quantization maintains firing behavior close to the full-precision baseline.
  arXiv  Detail & Related papers  (2026-04-15T23:55:11Z)
• Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models [94.68358825189738]
  We propose a post-training framework for verifiable domains that jointly optimize prediction accuracy and reasoning quality.<n>We evaluate VPS on chess, a controlled testbed where reasoning steps can be deterministically verified against engine signals.<n>VPS preserves accuracy while significantly improving reasoning quality, reducing win-rate error by up to 30% and restoring consistency to near saturation.
  arXiv  Detail & Related papers  (2026-04-03T15:19:46Z)
• LATA: Laplacian-Assisted Transductive Adaptation for Conformal Uncertainty in Medical VLMs [61.06744611795341]
  Medical vision-language models (VLMs) are strong zero-shot recognizers for medical imaging.<n>We propose texttttextbfLATA (Laplacian-Assisted Transductive Adaptation), a textittraining- and label-free refinement.<n>texttttextbfLATA sharpens zero-shot predictions without compromising exchangeability.
  arXiv  Detail & Related papers  (2026-02-19T16:45:38Z)
• Constraint-Rectified Training for Efficient Chain-of-Thought [60.52883907721588]
  Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs)<n>While longer reasoning traces can improve answer quality and unlock abilities such as self-correction, they also incur high inference costs and often introduce redundant steps, known as overthinking.<n>Recent research seeks to develop efficient reasoning strategies that balance reasoning length and accuracy.
  arXiv  Detail & Related papers  (2026-02-13T02:13:45Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Progressive Element-wise Gradient Estimation for Neural Network Quantization [2.1413624861650358]
  Quantization-Aware Training (QAT) methods rely on the Straight-Through Estimator (STE) to address the non-differentiability of discretization functions.<n>We propose Progressive Element-wise Gradient Estimation (PEGE) to address discretization errors between continuous and quantized values.<n>PEGE consistently outperforms existing backpropagation methods and enables low-precision models to match or even outperform the accuracy of their full-precision counterparts.
  arXiv  Detail & Related papers  (2025-08-27T15:59:36Z)
• End-to-End On-Device Quantization-Aware Training for LLMs at Inference Cost [53.25965863436039]
  Quantization-aware training (QAT) provides a more principled solution, but its reliance on backpropagation incurs prohibitive memory costs.<n>We propose ZeroQAT, a zeroth-order optimization-based QAT framework that supports both weight and activation quantization.<n>Experiments show that ZeroQAT consistently outperforms representative PTQ and QAT baselines while requiring significantly less memory.
  arXiv  Detail & Related papers  (2025-08-21T01:18:27Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Transferable Calibration with Lower Bias and Variance in Domain Adaptation [139.4332115349543]
  Domain Adaptation (DA) enables transferring a learning machine from a labeled source domain to an unlabeled target one. How to estimate the predictive uncertainty of DA models is vital for decision-making in safety-critical scenarios. TransCal can be easily applied to recalibrate existing DA methods.
  arXiv  Detail & Related papers  (2020-07-16T11:09:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.