Paper ID: 2303.03084

On Regression in Extreme Regions

Nathan Huet, Stephan Clémençon, Anne Sabourin

The statistical learning problem consists in building a predictive function $\hat{f}$ based on independent copies of $(X,Y)$ so that $Y$ is approximated by $\hat{f}(X)$ with minimum (squared) error. Motivated by various applications, special attention is paid here to the case of extreme (i.e. very large) observations $X$. Because of their rarity, the contributions of such observations to the (empirical) error is negligible, and the predictive performance of empirical risk minimizers can be consequently very poor in extreme regions. In this paper, we develop a general framework for regression on extremes. Under appropriate regular variation assumptions regarding the pair $(X,Y)$, we show that an asymptotic notion of risk can be tailored to summarize appropriately predictive performance in extreme regions. It is also proved that minimization of an empirical and nonasymptotic version of this 'extreme risk', based on a fraction of the largest observations solely, yields good generalization capacity. In addition, numerical results providing strong empirical evidence of the relevance of the approach proposed are displayed.

Submitted: Mar 6, 2023