paper-with-me

홈 › Papers

Guaranteed Bounds for Posterior Inference in Universal Probabilistic Programming

2022-04-06 · Raven Beutner, Luke Ong, Fabian Zaiser

We propose a new method to approximate the posterior distribution of probabilistic programs by means of computing guaranteed bounds. The starting point of our work is an interval-based trace semantics for a recursive, higher-order probabilistic programming language with continuous distributions. Taking the form of (super-/subadditive) measures, these lower/upper bounds are non-stochastic and provably correct: using the semantics, we prove that the actual posterior of a given program is sandwiched between the lower and upper bounds (soundness); moreover the bounds converge to the posterior (completeness). As a practical and sound approximation, we introduce a weight-aware interval type system, which automatically infers interval bounds on not just the return value but also weight of program executions, simultaneously. We have built a tool implementation, called GuBPI, which automatically computes these posterior lower/upper bounds. Our evaluation on examples from the literature shows that the bounds are useful, and can even be used to recognise wrong outputs from stochastic posterior inference procedures.

📄 PDF Abstract BibTeX arXiv:2204.02948

Code (0)

등록된 구현이 없습니다.

Tasks

Probabilistic Programming

Similar Papers 제목 키워드 기반

Attention for Inference Compilation

2019-10-25 · William Harvey, Andreas Munk, Atılım Güneş Baydin, Alexander Bergholm 외

We present a new approach to automatic amortized inference in universal probabilistic programs which improves performance compared to current methods. Our approach is a variation of inference compilation (IC) which lever…

Quantitative Verification of Omega-regular Properties in Probabilistic Programming

2025-12-25 · Peixin Wang, Jianhao Bai, Min Zhang, C. -H. Luke Ong arxiv

Probabilistic programming provides a high-level framework for specifying statistical models as executable programs with built-in randomness and conditioning. Existing inference techniques, however, typically compute post…

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees

2024-10-20 · Yijie Zhang

Bayesian inference provides a principled probabilistic framework for quantifying uncertainty by updating beliefs based on prior knowledge and observed data through Bayes' theorem. In Bayesian deep learning, neural networ…

Bayesian InferenceGeneralization Bounds

Challenges in Computing and Optimizing Upper Bounds of Marginal Likelihood based on Chi-Square Divergences

2019-10-16 · pproximateinference AABI Symposium 2019 12 · Melanie F. Pradier, Michael C. Hughes, Finale Doshi-Velez

Variational inference based on chi-square divergence minimization (CHIVI) provides a way to approximate a model's posterior while obtaining an upper bound on the marginal likelihood. However, in practice CHIVI relies on …

DiagnosticVariational Inference

MAS: a multiplicative approximation scheme for probabilistic inference

2008-12-01 · NeurIPS 2008 12 · Ydo Wexler, Christopher Meek

We propose a multiplicative approximation scheme (MAS) for inference problems in graphical models, which can be applied to various inference algorithms. The method uses $\epsilon$-decompositions which decompose functions…