Generative modeling via tree tensor network states
From MaRDI portal
Publication:6042367
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.
Cites work
- An introduction to matrix concentration inequalities
- Approximating discrete probability distributions with dependence trees
- Approximation and sampling of multivariate probability distributions in the tensor train decomposition
- Criticality, the Area Law, and the Computational Power of Projected Entangled Pair States
- Density estimation by dual ascent of the log-likelihood
- Efficient construction of tensor ring representations from sampling
- Fast construction of hierarchical matrix representation from matrix-vector multiplication
- Learning a tree-structured Ising model in order to make predictions
- Near-optimal learning of tree-structured distributions by Chow-Liu
- Numerical Linear Algebra
- Sketching as a tool for numerical linear algebra
- Spectral Methods for Data Science: A Statistical Perspective
- Tensor completion and low-\(n\)-rank tensor recovery via convex optimization
- Tensor-train decomposition
- Training Products of Experts by Minimizing Contrastive Divergence
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)
