Signal extraction approach for sparse multivariate response regression

TL;DR

This paper introduces a novel signal extraction method for high-dimensional multivariate response regression that optimally approximates the response function with nearly minimal prediction error, even with large or complex data.

Contribution

It proposes a new decomposition approach based on penalized generalized eigenvalue problems, extending theoretical guarantees to settings with correlated noise and high response dimensions.

Findings

Method achieves near-optimal prediction error.

Performs well in high-dimensional, correlated noise settings.

Demonstrates strong results in simulations and real data applications.

Abstract

In this paper, we consider multivariate response regression models with high dimensional predictor variables. One way to model the correlation among the response variables is through the low rank decomposition of the coefficient matrix, which has been considered by several papers for the high dimensional predictors. However, all these papers focus on the singular value decomposition of the coefficient matrix. Our target is the decomposition of the coefficient matrix which leads to the best lower rank approximation to the regression function, the signal part in the response. Given any rank, this decomposition has nearly the smallest expected prediction error among all approximations to the the coefficient matrix with the same rank. To estimate the decomposition, we formulate a penalized generalized eigenvalue problem to obtain the first matrix in the decomposition and then obtain the second one by a least squares method. In the high-dimensional setting, we establish the oracle inequalities for the estimates. Compared to the existing theoretical results, we have less restrictions on the distribution of the noise vector in each observation and allow correlations among its coordinates. Our theoretical results do not depend on the dimension of the multivariate response. Therefore, the dimension is arbitrary and can be larger than the sample size and the dimension of the predictor. Simulation studies and application to real data show that the proposed method has good prediction performance and is efficient in dimension reduction for various reduced rank models.