Generative modeling via tree tensor network states

DOI10.1007/S40687-023-00381-3arXiv2209.01341OpenAlexW4367308526MaRDI QIDQ6042367FDOQ6042367

Authors: Xun Tang, YoonHaeng Hur, Yuehaw Khoo, Lexing Ying 

Publication date: 10 May 2023

Published in: Research in the Mathematical Sciences (Search for Journal in Brave)

Abstract: In this paper, we present a density estimation framework based on tree tensor-network states. The proposed method consists of determining the tree topology with Chow-Liu algorithm, and obtaining a linear system of equations that defines the tensor-network components via sketching techniques. Novel choices of sketch functions are developed in order to consider graphical models that contain loops. Sample complexity guarantees are provided and further corroborated by numerical experiments.

Full work available at URL: https://arxiv.org/abs/2209.01341

zbMATH Keywords

curse of dimensionalitytensor networknon-iterative methodgenerative modelingtree tensor network states

Mathematics Subject Classification ID

Statistics (62-XX) Numerical analysis (65-XX)

Cites Work

• Approximating discrete probability distributions with dependence trees
• Tensor-train decomposition
• An introduction to matrix concentration inequalities
• Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
• Training Products of Experts by Minimizing Contrastive Divergence
• Criticality, the Area Law, and the Computational Power of Projected Entangled Pair States
• Fast construction of hierarchical matrix representation from matrix-vector multiplication
• Approximation and sampling of multivariate probability distributions in the tensor train decomposition
• Density estimation by dual ascent of the log-likelihood
• Sketching as a tool for numerical linear algebra
• Numerical Linear Algebra
• Efficient construction of tensor ring representations from sampling
• Learning a tree-structured Ising model in order to make predictions
• Spectral Methods for Data Science: A Statistical Perspective
• Near-optimal learning of tree-structured distributions by Chow-Liu

Cited In (1)

• High-dimensional density estimation with tensorizing flow

This page was built for publication: Generative modeling via tree tensor network states

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6042367)