Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making

• URL: http://arxiv.org/abs/2607.04019v1
• Date: Sat, 04 Jul 2026 20:30:48 GMT
• Title: Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Decision-Making
• Abstract summary: We introduce Finite Reliability Representations (FRR), a framework for covering belief spaces by reliability cells.<n>FRR is formulated on beliefs rather than states and uses a cover rather than an equivalence quotient.<n>It applies to finite POMDPs, linear-Gaussian filters, locally linearized nonlinear filters, and particle-filter implementations.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physical sensing and actuation noise floors should inform how much belief resolution a decision-making system can reliably use. We introduce Finite Reliability Representations (FRR), a framework for covering belief spaces by reliability cells: regions within which the optimal action-value function Q*(b,u) varies by at most a tolerance epsilon, uniformly over actions. The framework is formulated on beliefs rather than states and uses a cover rather than an equivalence quotient, because approximate decision-closeness is not transitive in general. A central technical point is that noisy Bayesian updates should not be treated as globally contractive on arbitrary beliefs. We therefore separate three objects: the fixed-observation filter map, the predictive observation law, and the controlled belief-transition kernel. For nonlinear continuous-state systems, FRR is obtained under a reachable-set Lipschitz modulus for the belief-transition kernel. For finite-state POMDPs, the same construction becomes exact on the belief simplex: prediction is linear, Bayesian correction is a normalized positive linear map, sensor noise enters through observation-distribution distinguishability, and actuation uncertainty enters through an action-execution channel. Under the corresponding action-value Lipschitz condition, an FRR cover supports a cell-constant policy whose suboptimality is bounded by 2 epsilon/(1 - gamma). We also introduce reliability entropy, the logarithm of the minimal number of reliability cells, as a measure of certified decision-relevant belief complexity. The framework distinguishes representation sufficiency from fundamental performance floors imposed by sensing, process, and actuation noise. It applies to finite POMDPs, linear-Gaussian filters, locally linearized nonlinear filters, and particle-filter implementations through analytic or empirical certification of reliability cells.

Related papers

• 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)
• KappaPlace: Learning Hyperspherical Uncertainty for Visual Place Recognition via Prototype-Anchored Supervision [3.7599363231894176]
  Visual Place Recognition (VPR) is critical for autonomous navigation.<n>Standard pipelines cannot reliably signal when a query is ambiguous or a match is likely incorrect.<n>We propose KappaPlace, a principled framework for learning uncertainty-aware VPR representations.
  arXiv  Detail & Related papers  (2026-05-19T06:45:27Z)
• BandPO: Bridging Trust Regions and Ratio Clipping via Probability-Aware Bounds for LLM Reinforcement Learning [49.25750348525603]
  BandPO replaces canonical clipping with Band, a unified theoretical operator that projects trust regions into dynamic, probability-aware clipping intervals.<n>We show that BandPO consistently outperforms canonical clipping and Clip-Higher, while robustly mitigating entropy collapse.
  arXiv  Detail & Related papers  (2026-03-05T08:03:05Z)
• Avoiding the Price of Adaptivity: Inference in Linear Contextual Bandits via Stability [2.5782420501870296]
  We argue that stability and statistical efficiency can coexist within a single contextual bandit method.<n>We show that our algorithm achieves regret guarantees that are minimax optimal up to logarithmic factors.
  arXiv  Detail & Related papers  (2025-12-23T13:53:53Z)
• Statistical Inference under Adaptive Sampling with LinUCB [15.167069362020426]
  We show that the linear upper confidence bound (LinUCB) algorithm for linear bandits satisfies a property called stability.<n>We establish a central limit theorem for the LinUCB algorithm, establishing normality for the limiting distribution of the estimation error.
  arXiv  Detail & Related papers  (2025-11-28T21:48:18Z)
• 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)
• Stability and performance guarantees for misspecified multivariate score-driven filters [0.0]
  We examine score-driven (ISD and ESD) filters, which update parameter predictions using the gradient of the logarithmic postulated observation density.<n>For both filter types, we derive novel sufficient conditions that ensure the exponential stability of the filtered parameter path.<n>We validate our theoretical findings through simulation studies, showing that ISD filters outperform ESD filters in terms of accuracy and stability.
  arXiv  Detail & Related papers  (2025-02-07T15:48:16Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Resampled Confidence Regions with Exponential Shrinkage for the Regression Function of Binary Classification [0.0]
  We build distribution-free confidence regions for the regression function for any user-chosen confidence level and any finite sample size based on a resampling test.<n>We prove the strong uniform consistency of a new empirical risk based approach for model classes with finite pseudo-dimensions and inverse Lipschitz parameterizations.<n>We also consider a k-nearest neighbors based method, for which we prove strong point boundswise on the probability of exclusion.
  arXiv  Detail & Related papers  (2023-08-03T15:52:27Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Sampling-Based Robust Control of Autonomous Systems with Non-Gaussian Noise [59.47042225257565]
  We present a novel planning method that does not rely on any explicit representation of the noise distributions. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP)
  arXiv  Detail & Related papers  (2021-10-25T06:18:55Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)

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.