When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates

• URL: http://arxiv.org/abs/2510.04769v1
• Date: Mon, 06 Oct 2025 12:42:32 GMT
• Title: When Do Credal Sets Stabilize? Fixed-Point Theorems for Credal Set Updates
• Authors: Michele Caprio, Siu Lun Chau, Krikamol Muandet,
• Abstract summary: In the presence of imprecision and ambiguity, credal sets have emerged as a popular framework for representing imprecise probabilistic beliefs.<n>We show that incorporating imprecision into the learning process not only enriches the representation of uncertainty, but also reveals structural conditions under which stability emerges.
• Score: 12.230769294623121
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many machine learning algorithms rely on iterative updates of uncertainty representations, ranging from variational inference and expectation-maximization, to reinforcement learning, continual learning, and multi-agent learning. In the presence of imprecision and ambiguity, credal sets -- closed, convex sets of probability distributions -- have emerged as a popular framework for representing imprecise probabilistic beliefs. Under such imprecision, many learning problems in imprecise probabilistic machine learning (IPML) may be viewed as processes involving successive applications of update rules on credal sets. This naturally raises the question of whether this iterative process converges to stable fixed points -- or, more generally, under what conditions on the updating mechanism such fixed points exist, and whether they can be attained. We provide the first analysis of this problem and illustrate our findings using Credal Bayesian Deep Learning as a concrete example. Our work demonstrates that incorporating imprecision into the learning process not only enriches the representation of uncertainty, but also reveals structural conditions under which stability emerges, thereby offering new insights into the dynamics of iterative learning under imprecision.

Related papers

• A Function-Space Stability Boundary for Generalization in Interpolating Learning Systems [0.0]
  We model training as a function-space trajectory and measure sensitivity to single-sample perturbations along this trajectory.<n>A small certificate implies stability-based generalization, while we also prove that there exist interpolating regimes with small risk.
  arXiv  Detail & Related papers  (2026-02-03T13:31:12Z)
• Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know [1.8613536568358358]
  This thesis advances the paradigm of Epistemic Artificial Intelligence, which explicitly models and quantifies uncertainty.<n>Central to this work is the development of the Random-Set Neural Network (RS-NN), a novel methodology that leverages random set theory to predict belief functions.<n>The title encapsulates the core philosophy of this work, emphasizing that true intelligence involves recognizing and managing the limits of one's own knowledge.
  arXiv  Detail & Related papers  (2025-10-25T12:00:19Z)
• Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning [1.2183405753834562]
  This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of machine learning (ML) systems.<n>We first show that a model's training trajectory contains rich uncertainty signals that can be exploited without altering its architecture or loss.<n>We propose a lightweight, post-hoc abstention method that works across tasks, avoids the cost of deep ensembles, and achieves state-of-the-art selective prediction performance.
  arXiv  Detail & Related papers  (2025-08-11T02:33:53Z)
• Variation Due to Regularization Tractably Recovers Bayesian Deep Learning [44.16006844888796]
  We propose an uncertainty quantification method for large networks based on variation due to regularization.<n>We show that regularization variation (RegVar) provides rigorous uncertainty estimates that, in the infinitesimal limit, exactly recover the Laplace approximation in Bayesian deep learning.<n>Our experiments across multiple datasets show that RegVar not only identifies uncertain predictions effectively but also provides insights into the stability of learned representations.
  arXiv  Detail & Related papers  (2024-03-15T20:47:39Z)
• Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling [69.83976050879318]
  In large language models (LLMs), identifying sources of uncertainty is an important step toward improving reliability, trustworthiness, and interpretability. In this paper, we introduce an uncertainty decomposition framework for LLMs, called input clarification ensembling. Our approach generates a set of clarifications for the input, feeds them into an LLM, and ensembles the corresponding predictions.
  arXiv  Detail & Related papers  (2023-11-15T05:58:35Z)
• 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)
• Calibrating Multimodal Learning [94.65232214643436]
  We propose a novel regularization technique, i.e., Calibrating Multimodal Learning (CML) regularization, to calibrate the predictive confidence of previous methods. This technique could be flexibly equipped by existing models and improve the performance in terms of confidence calibration, classification accuracy, and model robustness.
  arXiv  Detail & Related papers  (2023-06-02T04:29:57Z)
• The Unreasonable Effectiveness of Deep Evidential Regression [72.30888739450343]
  A new approach with uncertainty-aware regression-based neural networks (NNs) shows promise over traditional deterministic methods and typical Bayesian NNs. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a quantification rather than an exact uncertainty.
  arXiv  Detail & Related papers  (2022-05-20T10:10:32Z)
• Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model [68.34559610536614]
  We argue that the aleatoric uncertainty is an inherent attribute of the data and can only be correctly estimated with an unbiased oracle model. We propose a new sampling and selection strategy at train time to approximate the oracle model for aleatoric uncertainty estimation. Our results show that our solution achieves both accurate deterministic results and reliable uncertainty estimation.
  arXiv  Detail & Related papers  (2021-11-22T08:54:10Z)
• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification [58.03725169462616]
  We show theoretically that over-parametrization is not the only reason for over-confidence. We prove that logistic regression is inherently over-confident, in the realizable, under-parametrized setting. Perhaps surprisingly, we also show that over-confidence is not always the case.
  arXiv  Detail & Related papers  (2021-02-15T21:38:09Z)
• Uncertainty Estimation and Calibration with Finite-State Probabilistic RNNs [29.84563789289183]
  Uncertainty quantification is crucial for building reliable and trustable machine learning systems. We propose to estimate uncertainty in recurrent neural networks (RNNs) via discrete state transitions over recurrent timesteps. The uncertainty of the model can be quantified by running a prediction several times, each time sampling from the recurrent state transition distribution.
  arXiv  Detail & Related papers  (2020-11-24T10:35:28Z)
• Representations for Stable Off-Policy Reinforcement Learning [37.561660796265]
  Reinforcement learning with function approximation can be unstable and even divergent. We show that non-trivial state representations under which the canonical TD algorithm is stable, even when learning off-policy. We conclude by empirically demonstrating that these stable representations can be learned using gradient descent.
  arXiv  Detail & Related papers  (2020-07-10T17:55:54Z)

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.