MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation

• URL: http://arxiv.org/abs/2605.21783v1
• Date: Wed, 20 May 2026 22:22:20 GMT
• Title: MMD-Balls as Credal Sets: A PAC-Bayesian Framework for Epistemic Uncertainty in Test-Time Adaptation
• Abstract summary: Test-time adaptation methods improve model performance under distribution shift.<n>Test-time adaptation methods lack formal guarantees connecting shift magnitude to prediction reliability.<n>We develop a PAC-Bayesian framework yielding bounds explicitly parameterized by the maximum mean discrepancy (MMD) between source and target distributions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time adaptation (TTA) methods improve model performance under distribution shift but lack formal guarantees connecting shift magnitude to prediction reliability. We develop a PAC-Bayesian framework yielding generalization bounds explicitly parameterized by the maximum mean discrepancy (MMD) between source and target distributions. Our principal contribution is interpreting MMD-balls around the source distribution as credal sets in Walley's imprecise probability theory, yielding natural epistemic uncertainty quantification. We establish: (i) a PAC-Bayesian bound with an MMD-dependent shift penalty under an RKHS-Lipschitz loss assumption; (ii) a finite-sample version via MMD concentration; (iii) a uniform worst-case risk bound over all distributions in the credal set, with a lower-upper risk decomposition; and (iv) geodesic preservation bounds explaining why kernel-guided adaptation protects local feature geometry. The credal set interpretation separates epistemic from aleatoric uncertainty and provides a principled decision criterion for when adaptation is warranted.

Related papers

• KMM-CP: Practical Conformal Prediction under Covariate Shift via Selective Kernel Mean Matching [19.67518257951341]
  Conformal Prediction (CP) provides finite-sample coverage guarantees under exchangeability.<n>We propose KMM-CP, a conformal prediction framework based on Kernel Mean Matching (KMM)<n> Experiments on molecular property prediction benchmarks with realistic distribution shifts show that KMM-CP reduces coverage gap by over 50% compared to existing approaches.
  arXiv  Detail & Related papers  (2026-03-27T13:44:42Z)
• CREDO: Epistemic-Aware Conformalized Credal Envelopes for Regression [3.6457570471698095]
  We introduce CREDO, a simple "credal-then-conformalize" recipe that combines both strengths.<n> CREDO first builds an interpretable credal envelope that widens when local evidence is weak, then applies split conformal calibration on top of this envelope to guarantee marginal coverage.<n>This separation of roles yields prediction intervals that are interpretable.
  arXiv  Detail & Related papers  (2026-03-06T19:37:21Z)
• Accelerated Online Risk-Averse Policy Evaluation in POMDPs with Theoretical Guarantees and Novel CVaR Bounds [9.269394037577177]
  This work introduces a theoretical framework for accelerating Conditional Value-at-Risk evaluation in partially observable domains.<n>We establish upper and lower bounds on the CVaR value function computable from a simplified belief-MDP.<n>We develop estimators for these bounds within a particle-belief MDP framework with probabilistic guarantees.
  arXiv  Detail & Related papers  (2026-02-26T15:01:40Z)
• ProbFM: Probabilistic Time Series Foundation Model with Uncertainty Decomposition [0.12489632787815884]
  Time Series Foundation Models (TSFMs) have emerged as a promising approach for zero-shot financial forecasting.<n>Current approaches either rely on restrictive distributional assumptions, conflate different sources of uncertainty, or lack principled calibration mechanisms.<n>We present a novel transformer-based probabilistic framework, ProbFM, that leverages Deep Evidential Regression (DER) to provide principled uncertainty quantification.
  arXiv  Detail & Related papers  (2026-01-15T17:02:06Z)
• MMDCP: A Distribution-free Approach to Outlier Detection and Classification with Coverage Guarantees and SCW-FDR Control [6.429952624399788]
  We propose a unified framework for multi-class classification and outlier detection under label shift.<n>The Modified Mahalanobis Distance Conformal Prediction (MMDCP) combines class-specific distance measures with full conformal prediction to construct a score function.<n>We provide the first theoretical characterization of the gap between oracle and empirical conformal $p$-values, which ensures valid coverage and effective control of the class-wise false discovery rate (CW-FDR)
  arXiv  Detail & Related papers  (2025-11-15T03:48:44Z)
• 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)
• Diagnosing and Rectifying Fake OOD Invariance: A Restructured Causal Approach [51.012396632595554]
  Invariant representation learning (IRL) encourages the prediction from invariant causal features to labels de-confounded from the environments. Recent theoretical results verified that some causal features recovered by IRLs merely pretend domain-invariantly in the training environments but fail in unseen domains. We develop an approach based on conditional mutual information with respect to RS-SCM, then rigorously rectify the spurious and fake invariant effects.
  arXiv  Detail & Related papers  (2023-12-15T12:58:05Z)
• Policy Evaluation in Distributional LQR [70.63903506291383]
  We provide a closed-form expression of the distribution of the random return. We show that this distribution can be approximated by a finite number of random variables. Using the approximate return distribution, we propose a zeroth-order policy gradient algorithm for risk-averse LQR.
  arXiv  Detail & Related papers  (2023-03-23T20:27:40Z)
• Targeted Separation and Convergence with Kernel Discrepancies [61.973643031360254]
  kernel-based discrepancy measures are required to (i) separate a target P from other probability measures or (ii) control weak convergence to P.<n>In this article we derive new sufficient and necessary conditions to ensure (i) and (ii)<n>For MMDs on separable metric spaces, we characterize those kernels that separate Bochner embeddable measures and introduce simple conditions for separating all measures with unbounded kernels.
  arXiv  Detail & Related papers  (2022-09-26T16:41:16Z)
• Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach [150.8920602230832]
  We propose a framework for learning calibrated uncertainties under domain shifts. In particular, the density ratio estimation reflects the closeness of a target (test) sample to the source (training) distribution. We show that our proposed method generates calibrated uncertainties that benefit downstream tasks.
  arXiv  Detail & Related papers  (2020-10-08T02:10:54Z)
• Distributionally Robust Bayesian Quadrature Optimization [60.383252534861136]
  We study BQO under distributional uncertainty in which the underlying probability distribution is unknown except for a limited set of its i.i.d. samples. A standard BQO approach maximizes the Monte Carlo estimate of the true expected objective given the fixed sample set. We propose a novel posterior sampling based algorithm, namely distributionally robust BQO (DRBQO) for this purpose.
  arXiv  Detail & Related papers  (2020-01-19T12:00:33Z)

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.