paper-with-me

Papers

Generative Modeling via Tree Tensor Network States

2022-09-03 · Xun Tang, YoonHaeng Hur, Yuehaw Khoo, Lexing Ying

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.

📄 PDF Abstract BibTeX arXiv:2209.01341

Code (0)

등록된 구현이 없습니다.

Tasks

Density Estimation

Similar Papers 제목 키워드 기반

Tree Tensor Networks for Generative Modeling

2019-01-08 · Song Cheng, Lei Wang, Tao Xiang, Pan Zhang

Matrix product states (MPS), a tensor network designed for one-dimensional quantum systems, has been recently proposed for generative modeling of natural data (such as images) in terms of `Born machine'. However, the exp…

BIG-bench Machine LearningGPUTensor Networks

Supervised Learning with Projected Entangled Pair States

2020-09-12 · Song Cheng, Lei Wang, Pan Zhang

Tensor networks, a model that originated from quantum physics, has been gradually generalized as efficient models in machine learning in recent years. However, in order to achieve exact contraction, only tree-like tensor…

BIG-bench Machine LearningTensor Networks

Plastic tensor networks for interpretable generative modeling

2025-04-09 · Katsuya O. Akamatsu, Kenji Harada, Tsuyoshi Okubo, Naoki Kawashima

A structural optimization scheme for a single-layer nonnegative adaptive tensor tree (NATT) that models a target probability distribution is proposed. The NATT scheme, by construction, has the advantage that it is interp…

Tensor Networks

Unsupervised Generative Modeling Using Matrix Product States

2017-09-06 · Zhao-Yu Han, Jun Wang, Heng Fan, Lei Wang 외

Generative modeling, which learns joint probability distribution from data and generates samples according to it, is an important task in machine learning and artificial intelligence. Inspired by probabilistic interpreta…

BIG-bench Machine Learning

Comb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces

2024-12-08 · Danylo Kolesnyk, Yelyzaveta Vodovozova

Modern approaches to generative modeling of continuous data using tensor networks incorporate compression layers to capture the most meaningful features of high-dimensional inputs. These methods, however, rely on traditi…

Tensor Networks