Guaranteed Bounds for Posterior Inference in Universal Probabilistic Programming

04/06/2022
by   Raven Beutner, et al.
0

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.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

09/11/2015

Lazy Factored Inference for Functional Probabilistic Programming

Probabilistic programming provides the means to represent and reason abo...
04/12/2017

Eigenvalues of symmetric tridiagonal interval matrices revisited

In this short note, we present a novel method for computing exact lower ...
11/30/2020

Quantitative Analysis of Assertion Violations in Probabilistic Programs

In this work, we consider the fundamental problem of deriving quantitati...
01/16/2014

Active Tuples-based Scheme for Bounding Posterior Beliefs

The paper presents a scheme for computing lower and upper bounds on the ...
03/13/2013

Interval Structure: A Framework for Representing Uncertain Information

In this paper, a unified framework for representing uncertain informatio...
06/09/2021

Expectation Programming

Building on ideas from probabilistic programming, we introduce the conce...
01/20/2020

Probabilistic Output Analyses for Deterministic Programs — Reusing Existing Non-probabilistic Analyses

We consider reusing established non-probabilistic output analyses (eithe...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.