Learning with tree tensor networks: complexity estimates and model selection

TL;DR

This paper introduces a complexity-based model selection method for tree tensor networks, providing theoretical guarantees and practical algorithms that adapt to various smoothness classes in high-dimensional function approximation.

Contribution

It develops a penalized empirical risk minimization framework for selecting tree tensor network models with theoretical risk bounds and adaptive minimax optimality.

Findings

The proposed method achieves near-minimax rates across multiple smoothness classes.

Risk bounds are derived based on metric entropy estimates for tree tensor networks.

Numerical experiments demonstrate effective model selection and improved approximation performance.

Abstract

Tree tensor networks, or tree-based tensor formats, are prominent model classes for the approximation of high-dimensional functions in computational and data science. They correspond to sum-product neural networks with a sparse connectivity associated with a dimension tree and widths given by a tuple of tensor ranks. The approximation power of these models has been proved to be (near to) optimal for classical smoothness classes. However, in an empirical risk minimization framework with a limited number of observations, the dimension tree and ranks should be selected carefully to balance estimation and approximation errors. We propose and analyze a complexity-based model selection method for tree tensor networks in an empirical risk minimization framework and we analyze its performance over a wide range of smoothness classes. Given a family of model classes associated with different trees, ranks, tensor product feature spaces and sparsity patterns for sparse tensor networks, a model is selected (\`a la Barron, Birg\'e, Massart) by minimizing a penalized empirical risk, with a penalty depending on the complexity of the model class and derived from estimates of the metric entropy of tree tensor networks. This choice of penalty yields a risk bound for the selected predictor. In a least-squares setting, after deriving fast rates of convergence of the risk, we show that our strategy is (near to) minimax adaptive to a wide range of smoothness classes including Sobolev or Besov spaces (with isotropic, anisotropic or mixed dominating smoothness) and analytic functions. We discuss the role of sparsity of the tensor network for obtaining optimal performance in several regimes. In practice, the amplitude of the penalty is calibrated with a slope heuristics method. Numerical experiments in a least-squares regression setting illustrate the performance of the strategy.