Testing Probabilistic Circuits

12/09/2021
by   Yash Pote, et al.
0

Probabilistic circuits (PCs) are a powerful modeling framework for representing tractable probability distributions over combinatorial spaces. In machine learning and probabilistic programming, one is often interested in understanding whether the distributions learned using PCs are close to the desired distribution. Thus, given two probabilistic circuits, a fundamental problem of interest is to determine whether their distributions are close to each other. The primary contribution of this paper is a closeness test for PCs with respect to the total variation distance metric. Our algorithm utilizes two common PC queries, counting and sampling. In particular, we provide a poly-time probabilistic algorithm to check the closeness of two PCs when the PCs support tractable approximate counting and sampling. We demonstrate the practical efficiency of our algorithmic framework via a detailed experimental evaluation of a prototype implementation against a set of 475 PC benchmarks. We find that our test correctly decides the closeness of all 475 PCs within 3600 seconds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/19/2021

Probabilistic Generating Circuits

Generating functions, which are widely used in combinatorics and probabi...
research
06/26/2020

On the Relationship Between Probabilistic Circuits and Determinantal Point Processes

Scaling probabilistic models to large realistic problems and datasets is...
research
01/03/2023

Unconditional Quantum Advantage for Sampling with Shallow Circuits

Recent work by Bravyi, Gosset, and Koenig showed that there exists a sea...
research
10/24/2022

Protocols for classically training quantum generative models on probability distributions

Quantum Generative Modelling (QGM) relies on preparing quantum states an...
research
04/13/2020

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuits

Probabilistic circuits (PCs) are a promising avenue for probabilistic mo...
research
01/17/2019

Learning Tractable Probabilistic Models in Open Worlds

Large-scale probabilistic representations, including statistical knowled...
research
09/13/2023

A Cancellation Law for Probabilistic Processes

We show a cancellation property for probabilistic choice. If distributio...

Please sign up or login with your details

Forgot password? Click here to reset