The Lifecycle of a Statistical Model: Model Failure Detection, Identification, and Refitting

TL;DR

This paper introduces methods for detecting, identifying, and fixing subpopulations where statistical models fail, enhancing model robustness in real-world applications through empirical validation and theoretical guarantees.

Contribution

It develops a novel framework for detecting and refitting models in failure regions, supported by theory and empirical results on real-world datasets including COVID-19 forecasting.

Findings

Method effectively detects model failure regions.

Refitting improves overall model accuracy.

Framework is minimax optimal for identifying anomalies.

Abstract

The statistical machine learning community has demonstrated considerable resourcefulness over the years in developing highly expressive tools for estimation, prediction, and inference. The bedrock assumptions underlying these developments are that the data comes from a fixed population and displays little heterogeneity. But reality is significantly more complex: statistical models now routinely fail when released into real-world systems and scientific applications, where such assumptions rarely hold. Consequently, we pursue a different path in this paper vis-a-vis the well-worn trail of developing new methodology for estimation and prediction. In this paper, we develop tools and theory for detecting and identifying regions of the covariate space (subpopulations) where model performance has begun to degrade, and study intervening to fix these failures through refitting. We present empirical results with three real-world data sets -- including a time series involving forecasting the incidence of COVID-19 -- showing that our methodology generates interpretable results, is useful for tracking model performance, and can boost model performance through refitting. We complement these empirical results with theory proving that our methodology is minimax optimal for recovering anomalous subpopulations as well as refitting to improve accuracy in a structured normal means setting.