Saved in:
Bibliographic Details
Main Authors: Loconte, Lorenzo, Mari, Antonio, Gala, Gennaro, Peharz, Robert, de Campos, Cassio, Quaeghebeur, Erik, Vessio, Gennaro, Vergari, Antonio
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.07953
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917909321744384
author Loconte, Lorenzo
Mari, Antonio
Gala, Gennaro
Peharz, Robert
de Campos, Cassio
Quaeghebeur, Erik
Vessio, Gennaro
Vergari, Antonio
author_facet Loconte, Lorenzo
Mari, Antonio
Gala, Gennaro
Peharz, Robert
de Campos, Cassio
Quaeghebeur, Erik
Vessio, Gennaro
Vergari, Antonio
contents This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these fields, we highlight a series of opportunities that can benefit both communities. Our work generalizes popular tensor factorizations within the circuit language, and unifies various circuit learning algorithms under a single, generalized hierarchical factorization framework. Specifically, we introduce a modular "Lego block" approach to build tensorized circuit architectures. This, in turn, allows us to systematically construct and explore various circuit and tensor factorization models while maintaining tractability. This connection not only clarifies similarities and differences in existing models, but also enables the development of a comprehensive pipeline for building and optimizing new circuit/tensor factorization architectures. We show the effectiveness of our framework through extensive empirical evaluations, and highlight new research opportunities for tensor factorizations in probabilistic modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2409_07953
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
Loconte, Lorenzo
Mari, Antonio
Gala, Gennaro
Peharz, Robert
de Campos, Cassio
Quaeghebeur, Erik
Vessio, Gennaro
Vergari, Antonio
Machine Learning
This paper establishes a rigorous connection between circuit representations and tensor factorizations, two seemingly distinct yet fundamentally related areas. By connecting these fields, we highlight a series of opportunities that can benefit both communities. Our work generalizes popular tensor factorizations within the circuit language, and unifies various circuit learning algorithms under a single, generalized hierarchical factorization framework. Specifically, we introduce a modular "Lego block" approach to build tensorized circuit architectures. This, in turn, allows us to systematically construct and explore various circuit and tensor factorization models while maintaining tractability. This connection not only clarifies similarities and differences in existing models, but also enables the development of a comprehensive pipeline for building and optimizing new circuit/tensor factorization architectures. We show the effectiveness of our framework through extensive empirical evaluations, and highlight new research opportunities for tensor factorizations in probabilistic modeling.
title What is the Relationship between Tensor Factorizations and Circuits (and How Can We Exploit it)?
topic Machine Learning
url https://arxiv.org/abs/2409.07953