Bucket renormalization for approximate inference

DOI10.1088/1742-5468/AB3218MaRDI QIDQ5854127zbMATH OpenOpenAlexFDO

Authors Sungsoo Ahn, Michael Chertkov, Adrian Weller, Jinwoo Shin

Publication date 16 March 2021

Published in Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1803.05104

Mathematics Subject Classification ID

Computational methods for problems pertaining to statistics (62-08) Probabilistic graphical models (62H22) Approximation algorithms (68W25)

Abstract: Probabilistic graphical models are a key tool in machine learning applications. Computing the partition function, i.e., normalizing constant, is a fundamental task of statistical inference but it is generally computationally intractable, leading to extensive study of approximation methods. Iterative variational methods are a popular and successful family of approaches. However, even state of the art variational methods can return poor results or fail to converge on difficult instances. In this paper, we instead consider computing the partition function via sequential summation over variables. We develop robust approximate algorithms by combining ideas from mini-bucket elimination with tensor network and renormalization group methods from statistical physics. The resulting "convergence-free" methods show good empirical performance on both synthetic and real-world benchmark models, even for difficult instances.

Recommendations

• Gauging variational inference
• Graphical models, exponential families, and variational inference
• A New Class of Upper Bounds on the Log Partition Function
• scientific article; zbMATH DE number 1315583
• Approximate methods for calculating marginals and likelihoods

Cites work

• scientific article; zbMATH DE number 15992 (Why is no real title available?)
• scientific article; zbMATH DE number 6317138 (Why is no real title available?)
• A New Class of Upper Bounds on the Log Partition Function
• Bucket elimination: A unifying framework for reasoning
• Codes on graphs: normal realizations
• Crystal Statistics. I. A Two-Dimensional Model with an Order-Disorder Transition
• Learning low-level vision
• Mini-buckets: a general scheme for bounded inference
• Polynomial-Time Approximation Algorithms for the Ising Model
• Probabilistic graphical models.
• Probability propagation
• Reducing the Dimensionality of Data with Neural Networks
• Statistical field theory. With a foreword by David Pines

Cited in

(1)

• Gauging variational inference

Describes a project that uses

Uses Software

• darch

This page was built for publication: Bucket renormalization for approximate inference

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5854127)