Deep distribution regression
Rui Li, Brian J Reich, Howard D Bondell
COMPUTATIONAL STATISTICS & DATA ANALYSIS | ELSEVIER | Published : 2021
Due to their flexibility and predictive performance, machine-learning based regression methods have become an important tool for predictive modeling and forecasting. However, most methods focus on estimating the conditional mean or specific quantiles of the target quantity and do not provide the full conditional distribution, which contains uncertainty information that might be crucial for decision making. A general solution consists of transforming a conditional distribution estimation problem into a constrained multi-class classification problem, in which tools such as deep neural networks can be applied. A novel joint binary cross-entropy loss function is proposed to accomplish this goal...View full abstract
Awarded by King Abdullah University of Science and Technology, Saudi Arabia
The authors' work was partially supported by King Abdullah University of Science and Technology, Saudi Arabia (grant number 3800.2).