Generative Modeling via Tree Tensor Network States
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Density EstimationSimilar Papers 제목 키워드 기반
Tree Tensor Networks for Generative Modeling
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 NetworksSupervised Learning with Projected Entangled Pair States
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 NetworksPlastic tensor networks for interpretable generative modeling
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 NetworksUnsupervised Generative Modeling Using Matrix Product States
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 LearningComb Tensor Networks vs. Matrix Product States: Enhanced Efficiency in High-Dimensional Spaces
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