Generative modeling via tensor train sketching

Abstract

In this paper we introduce a sketching algorithm for constructing a tensor train representation of a probability density from its samples. Our method deviates from the standard recursive SVD-based procedure for constructing a tensor train. Instead we formulate and solve a sequence of small linear systems for the individual tensor train cores. This approach can avoid the curse of dimensionality that threatens both the algorithmic and sample complexities of the recovery problem. Specifically, for Markov models, we prove that the tensor cores can be recovered with a sample complexity that is constant with respect to the dimension. Finally, we illustrate the performance of the method with several numerical experiments.

Atomic Quantum Technologies for Quantum Matter and Fundamental Physics Applications

“…Since then, the TN formalism has been applied to the network structures native to ML, formally understanding their equivalence [417], allowing for the compression and simplification of ML algorithms by exploiting the TN structure [418], characterising their expressivity [419] or being able to adapt tensor network algorithms such as DMRG to their language [420]; also intertwining with Bayesian based-protocols [421] or generative modeling [422]. In the same way, ML approaches can be used to accelerate operations in TN [423].…”