Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift

• URL: http://arxiv.org/abs/2605.17212v2
• Date: Thu, 21 May 2026 18:25:09 GMT
• Title: Anytime PAC-Bayes for Constrained Density-Ratio Networks under Covariate Shift
• Abstract summary: PAC-Bayes is instantiated on the weighted risk in a fixed-time regime that yields Bernoulli-KL bounds.<n>A patch test against analytic ground truth with a real-data deployment validates the framework.<n>A single fixed-time coverage failure is recorded, with per-split coverage aligning one-to-one with the magnitude of the label shift.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A unified framework for learning under covariate shift is presented, in which a constrained density-ratio network approximates the Radon-Nikodym derivative $r^\star = dP/dQ$ and feeds an anytime PAC-Bayes generalization certificate. A change-of-measure identity decomposes the gap between target risk and importance-weighted source risk into a ratio-bias term governed by $\|r_θ- r^\star\|_{L^2(Q)}$ and a generalization-gap term governed by the variability of the weighted loss. Normalization and moment-matching identities are enforced as hard integral constraints through an augmented-Lagrangian scheme, with a second-moment penalty controlling the effective sample size. PAC-Bayes is instantiated on the weighted risk in a fixed-time regime that yields Bernoulli-KL bounds, identifies the network-weighted Gibbs posterior as the unique KL-regularized minimizer, and quantifies stability under $L^2(Q)$ perturbations of the learned ratio, and is then strengthened by geometric peeling to an anytime certificate uniform in $t \geq t_{\min}$. A pre-registered two-campaign protocol combining a patch test against analytic ground truth with a real-data deployment validates the framework: the network produces calibrated ratios, reduces target $0/1$ loss against unweighted ERM and classical direct ratio-estimation baselines, and attains the anytime certificate. A single fixed-time coverage failure is recorded, with per-split coverage aligning one-to-one with the magnitude of the label shift, confirming that the covariate-only assumption is operationally tight rather than a defect of the certificate.

Related papers

• Counterfactual Shapley Credit Assignment [49.39649767581182]
  Credit Assignment Problem (CAP) is fundamental to developing efficient and explainable Reinforcement Learning (RL) agents.<n>We introduce Counterfactual Shapley Credit Assignment, a novel framework that attributes credit and blame via the Counterfactual Shapley ($$-value)<n>We derive a consistent estimator that computes $$$-values, enabling a new class of policy methods, $$-PPO, combined with Prioritized Trajectory Replay (PTR)
  arXiv  Detail & Related papers  (2026-07-18T23:28:20Z)
• The SIGReg Objective as Variational Free Energy: A Theoretical Active-Inference Account of JEPA World Models [47.471225029744424]
  Joint-Embedding Predictive Architectures (JEPAs) are the dominant design for latent world models.<n>We show that the choice of anti-collapse regulariser determines whether a JEPA's training objective, a prediction loss plus a weighted embedding regulariser, is a valid Active Inference (AIF) variational free energy.
  arXiv  Detail & Related papers  (2026-07-15T08:59:36Z)
• Best-Arm Identification with Generative Proxy [10.674965991983974]
  We study fixed-confidence best-arm identification in which each costly reward pull is paired with a cheap but correlated proxy score.<n>We propose PROBE, a phase-elimination algorithm that maintains an upper certificate on the residual variance with an ordinary least squares fit.<n>We prove that PROBE is $$-PAC and attains the known-correlation oracle sample complexity up to a constant multiplicative factor and a constant additive calibration cost.
  arXiv  Detail & Related papers  (2026-07-08T00:41:43Z)
• Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration [20.21455697379946]
  We propose Decoupled Conformal optimisation (DCO) as a train-tune-calibrate design principle.<n>DCO uses an independent tuning split for efficiency-oriented structural selection and a fresh calibration split for the final conformal quantile.<n>We show that DCO tracks the nominal coverage level closely while often reducing average prediction-set size or interval width relative to PAC-style calibration.
  arXiv  Detail & Related papers  (2026-05-18T13:10:21Z)
• Disagreement-Regularized Importance Sampling for Adversarial Label Corruption [3.0416928830191066]
  Disagreement-Regularized Importance Sampling (DR-IS) is a sub-sampling method based on loss rank-disagreement across independent proxy ensemble.<n>DR-IS is robust under targeted high-norm attacks that break magnitude-based methods such as the Error $L$-norm (EL2N) on benchmark datasets.
  arXiv  Detail & Related papers  (2026-05-08T10:27:51Z)
• Non-monotonicity in Conformal Risk Control [4.71350885287928]
  Conformal risk control (CRC) provides distribution-free guarantees for controlling the expected loss at a user-specified level.<n>We study CRC under non-monotone loss functions when the tuning parameter is selected from a finite grid.<n>We show that the validity of CRC without monotonicity depends on the relationship between the calibration sample size and the grid resolution.
  arXiv  Detail & Related papers  (2026-04-02T00:26:50Z)
• Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions [89.52532304099522]
  Federated Learning (FL) enables clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy.<n> gradients and model updates can still leak sensitive information, while malicious servers may mount adversarial attacks such as Byzantine manipulation.<n>These vulnerabilities highlight the need to address differential privacy (DP) and Byzantine robustness within a unified framework.<n>We propose Byz-Clip21-SGD2M, a new algorithm that integrates robust aggregation with double momentum and carefully designed clipping.
  arXiv  Detail & Related papers  (2026-03-24T17:39:09Z)
• Improving Search Agent with One Line of Code [68.58667107354253]
  Tool-based Agentic Reinforcement Learning (TARL) has emerged as a promising paradigm for training search agents to interact with external tools.<n>We propose textbfSearch textbfAgent textbfPolicy textbfOptimization (textbfSAPO), which stabilizes training via a conditional token-level KL constraint.
  arXiv  Detail & Related papers  (2026-03-10T04:07:39Z)
• Stability and Generalization of Push-Sum Based Decentralized Optimization over Directed Graphs [55.77845440440496]
  Push-based decentralized communication enables optimization over communication networks, where information exchange may be asymmetric.<n>We develop a unified uniform-stability framework for the Gradient Push (SGP) algorithm.<n>A key technical ingredient is an imbalance-aware generalization bound through two quantities.
  arXiv  Detail & Related papers  (2026-02-24T05:32:03Z)
• Concave Certificates: Geometric Framework for Distributionally Robust Risk and Complexity Analysis [0.7106986689736828]
  Distributionally Robust (DR) optimization aims to certify worst-case risk within a Wasserstein uncertainty set.<n>This paper introduces a novel geometric framework based on the least concave majorants of the growth rate function.<n>We extend this framework to complexity analysis, introducing a deterministic bound that complements standard statistical bound.
  arXiv  Detail & Related papers  (2026-01-04T00:24:43Z)
• ZIP-RC: Optimizing Test-Time Compute via Zero-Overhead Joint Reward-Cost Prediction [57.799425838564]
  We present ZIP-RC, an adaptive inference method that equips models with zero-overhead inference-time predictions of reward and cost.<n> ZIP-RC improves accuracy by up to 12% over majority voting at equal or lower average cost.
  arXiv  Detail & Related papers  (2025-12-01T09:44:31Z)
• Wasserstein-regularized Conformal Prediction under General Distribution Shift [21.29977879431466]
  Conformal prediction yields a prediction set with guaranteed $1-alpha$ coverage of the true target under the i.i.d. assumption.<n>We propose a Wasserstein distance-based upper bound of the coverage gap and analyze the bound using probability measure pushforwards.<n>We exploit the separation to design an algorithm based on importance weighting and regularized representation learning (WR-CP) to reduce the Wasserstein bound with a finite-sample error bound.
  arXiv  Detail & Related papers  (2025-01-23T07:29:44Z)
• Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning [57.88785630755165]
  Empirical risk minimization (ERM) is the workhorse of machine learning, but its model-agnostic guarantees can fail when we use adaptively collected data. We study a generic importance sampling weighted ERM algorithm for using adaptively collected data to minimize the average of a loss function over a hypothesis class. For policy learning, we provide rate-optimal regret guarantees that close an open gap in the existing literature whenever exploration decays to zero.
  arXiv  Detail & Related papers  (2021-06-03T09:50:13Z)
• Doubly Robust Off-Policy Actor-Critic: Convergence and Optimality [131.45028999325797]
  We develop a doubly robust off-policy AC (DR-Off-PAC) for discounted MDP. DR-Off-PAC adopts a single timescale structure, in which both actor and critics are updated simultaneously with constant stepsize. We study the finite-time convergence rate and characterize the sample complexity for DR-Off-PAC to attain an $epsilon$-accurate optimal policy.
  arXiv  Detail & Related papers  (2021-02-23T18:56:13Z)

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.