Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems

TL;DR

This paper introduces a mutual information-based framework for regression, providing theoretical convergence analysis and demonstrating that high-dimensional data can be advantageous under this approach.

Contribution

It extends mutual information supervised learning to regression, offers a convergence analysis for SGD, and derives a generalization bound highlighting benefits of high dimensionality.

Findings

MSE minimization is equivalent to conditional entropy learning.

Proposed mutual information formulation for regression with reparameterization.

High dimensionality can improve generalization performance.

Abstract

As one of the central tasks in machine learning, regression finds lots of applications in different fields. An existing common practice for solving regression problems is the mean square error (MSE) minimization approach or its regularized variants which require prior knowledge about the models. Recently, Yi et al., proposed a mutual information based supervised learning framework where they introduced a label entropy regularization which does not require any prior knowledge. When applied to classification tasks and solved via a stochastic gradient descent (SGD) optimization algorithm, their approach achieved significant improvement over the commonly used cross entropy loss and its variants. However, they did not provide a theoretical convergence analysis of the SGD algorithm for the proposed formulation. Besides, applying the framework to regression tasks is nontrivial due to the potentially infinite support set of the label. In this paper, we investigate the regression under the mutual information based supervised learning framework. We first argue that the MSE minimization approach is equivalent to a conditional entropy learning problem, and then propose a mutual information learning formulation for solving regression problems by using a reparameterization technique. For the proposed formulation, we give the convergence analysis of the SGD algorithm for solving it in practice. Finally, we consider a multi-output regression data model where we derive the generalization performance lower bound in terms of the mutual information associated with the underlying data distribution. The result shows that the high dimensionality can be a bless instead of a curse, which is controlled by a threshold. We hope our work will serve as a good starting point for further research on the mutual information based regression.