Data-Driven Invariant Learning for Probabilistic Programs

06/09/2021
by   Jialu Bao, et al.
0

Morgan and McIver's weakest pre-expectation framework is one of the most well-established methods for deductive verification of probabilistic programs. Roughly, the idea is to generalize binary state assertions to real-valued expectations. While loop-free programs can be analyzed by mechanically transforming expectations, verifying loops usually requires finding an invariant expectation, a difficult task. We propose a new view of invariant expectation synthesis as a regression problem: given an input state, predict the average value of the post-expectation. Guided by this perspective, we develop the first data-driven invariant synthesis method for probabilistic programs. Unlike prior work on probabilistic invariant inference, our approach can learn piecewise continuous invariants without relying on template expectations, and also works when only given black-box access to the program. We implement our approach and demonstrate its effectiveness on a variety of benchmarks from the probabilistic programming literature.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

07/07/2017

Data-Driven Loop Invariant Inference with Automatic Feature Synthesis

We present LoopInvGen, a tool for generating loop invariants that can pr...
03/17/2020

Learning Nonlinear Loop Invariants with Gated Continuous Logic Networks

In many cases, verifying real-world programs requires inferring loop inv...
03/17/2020

Learning Nonlinear Loop Invariants with Gated Continuous Logic Networks (Extended Version)

Verifying real-world programs often requires inferring loop invariants w...
09/28/2021

Expectation-based Minimalist Grammars

Expectation-based Minimalist Grammars (e-MGs) are simplified versions of...
03/14/2018

An Assertion-Based Program Logic for Probabilistic Programs

Research on deductive verification of probabilistic programs has conside...
06/09/2021

Expectation Programming

Building on ideas from probabilistic programming, we introduce the conce...
04/25/2016

Generalized Homogeneous Polynomials for Efficient Template-Based Nonlinear Invariant Synthesis

The template-based method is one of the most successful approaches to al...
This week in AI

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