paper-with-me

Papers

Probabilistic unifying relations for modelling epistemic and aleatoric uncertainty: semantics and automated reasoning with theorem proving

2023-03-16 · Kangfeng Ye, Jim Woodcock, Simon Foster

Probabilistic programming combines general computer programming, statistical inference, and formal semantics to help systems make decisions when facing uncertainty. Probabilistic programs are ubiquitous, including having a significant impact on machine intelligence. While many probabilistic algorithms have been used in practice in different domains, their automated verification based on formal semantics is still a relatively new research area. In the last two decades, it has attracted much interest. Many challenges, however, remain. The work presented in this paper, probabilistic unifying relations (ProbURel), takes a step towards our vision to tackle these challenges. Our work is based on Hehner's predicative probabilistic programming, but there are several obstacles to the broader adoption of his work. Our contributions here include (1) the formalisation of its syntax and semantics by introducing an Iverson bracket notation to separate relations from arithmetic; (2) the formalisation of relations using Unifying Theories of Programming (UTP) and probabilities outside the brackets using summation over the topological space of the real numbers; (3) the constructive semantics for probabilistic loops using Kleene's fixed-point theorem; (4) the enrichment of its semantics from distributions to subdistributions and superdistributions to deal with the constructive semantics; (5) the unique fixed-point theorem to simplify the reasoning about probabilistic loops; and (6) the mechanisation of our theory in Isabelle/UTP, an implementation of UTP in Isabelle/HOL, for automated reasoning using theorem proving. We demonstrate our work with six examples, including problems in robot localisation, classification in machine learning, and the termination of probabilistic loops.

📄 PDF Abstract BibTeX arXiv:2303.09692

Code (0)

등록된 구현이 없습니다.

Tasks

Automated Theorem ProvingProbabilistic Programming

Similar Papers 제목 키워드 기반

HybridFlow: Quantification of Aleatoric and Epistemic Uncertainty with a Single Hybrid Model

2025-10-06 · Peter Van Katwyk, Karianne J. Bergen arxiv

Uncertainty quantification is critical for ensuring robustness in high-stakes machine learning applications. We introduce HybridFlow, a modular hybrid architecture that unifies the modeling of aleatoric and epistemic unc…

Depth Estimation

Rethinking Aleatoric and Epistemic Uncertainty

2024-12-30 · Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk 외

The ideas of aleatoric and epistemic uncertainty are widely used to reason about the probabilistic predictions of machine-learning models. We identify incoherence in existing discussions of these ideas and suggest this s…

On the Calibration of Probabilistic Classifier Sets

2022-05-20 · Thomas Mortier, Viktor Bengs, Eyke Hüllermeier, Stijn Luca 외

Multi-class classification methods that produce sets of probabilistic classifiers, such as ensemble learning methods, are able to model aleatoric and epistemic uncertainty. Aleatoric uncertainty is then typically quantif…

Ensemble LearningMulti-class Classification

Intrinsic Randomness in Epidemic Modelling Beyond Statistical Uncertainty

2022-10-25 · Matthew J. Penn, Daniel J. Laydon, Joseph Penn, Charles Whittaker 외

Uncertainty can be classified as either aleatoric (intrinsic randomness) or epistemic (imperfect knowledge of parameters). The majority of frameworks assessing infectious disease risk consider only epistemic uncertainty.…

Epistemic Uncertainty Sampling

2019-08-31 · Vu-Linh Nguyen, Sébastien Destercke, Eyke Hüllermeier

Various strategies for active learning have been proposed in the machine learning literature. In uncertainty sampling, which is among the most popular approaches, the active learner sequentially queries the label of thos…

Active Learning