Convex Regularization for High-Dimensional Multi-Response Tensor Regression

TL;DR

This paper introduces a convex optimization framework for high-dimensional multi-response tensor regression that leverages low-dimensional structures, providing general risk bounds and demonstrating minimax optimality across various models.

Contribution

It presents the first general convex regularization framework for multi-response tensor regression with theoretical risk bounds based on Gaussian width and intrinsic dimension.

Findings

Provides risk bounds for tensor regression models.

Demonstrates minimax optimality of estimates.

Validates theoretical results with numerical experiments.

Abstract

In this paper we present a general convex optimization approach for solving high-dimensional multiple response tensor regression problems under low-dimensional structural assumptions. We consider using convex and weakly decomposable regularizers assuming that the underlying tensor lies in an unknown low-dimensional subspace. Within our framework, we derive general risk bounds of the resulting estimate under fairly general dependence structure among covariates. Our framework leads to upper bounds in terms of two very simple quantities, the \emph{Gaussian width} of a convex set in tensor space and the \emph{intrinsic dimension} of the low-dimensional tensor subspace. To the best of our knowledge, this is the first general framework that applies to multiple response problems. These general bounds provide useful upper bounds on rates of convergence for a number of fundamental statistical models of interest including multi-response regression, vector auto-regressive models, low-rank tensor models and pairwise interaction models. Moreover, in many of these settings we prove that the resulting estimates are minimax optimal. We also provide a numerical study that both validates our theoretical guarantees and demonstrates the breadth of our framework.