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

arXiv: https://arxiv.org/abs/2202.04166 · HTML: https://mlsanity.com/paper/2202.04166/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 74 references that are in the map.
- First posted on arXiv 8 Feb 2022.

## Builds on (most cited first, 18 of 18)

- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Distribution-Free Predictive Inference For Regression](https://mlsanity.com/paper/1604.04173/) (2016)
- [Conformalized Quantile Regression](https://mlsanity.com/paper/1905.03222/) (2019)
- [Snorkel: Rapid Training Data Creation with Weak Supervision](https://mlsanity.com/paper/1711.10160/) (2017)
- [Data Programming: Creating Large Training Sets, Quickly](https://mlsanity.com/paper/1605.07723/) (2016)
- [Time-uniform, nonparametric, nonasymptotic confidence sequences](https://mlsanity.com/paper/1810.08240/) (2018)
- [Testing for Outliers with Conformal p-values](https://mlsanity.com/paper/2104.08279/) (2021)
- [Classification accuracy as a proxy for two sample testing](https://mlsanity.com/paper/1602.02210/) (2016)
- [Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices](https://mlsanity.com/paper/1909.06349/) (2019)
- [Always Valid Inference: Bringing Sequential Analysis to A/B Testing](https://mlsanity.com/paper/1512.04922/) (2015)
- [Choosing Between Methods of Combining p-values](https://mlsanity.com/paper/1707.06897/) (2017)
- [Predictive Inference with Weak Supervision](https://mlsanity.com/paper/2201.08315/) (2022)
- [The knockoff filter for FDR control in group-sparse and multitask regression](https://mlsanity.com/paper/1602.03589/) (2016)
- [A unified treatment of multiple testing with prior knowledge using the p-filter](https://mlsanity.com/paper/1703.06222/) (2017)
- [Near-optimal Anomaly Detection in Graphs using Lovasz Extended Scan Statistic](https://mlsanity.com/paper/1312.3291/) (2013)
- [Model Adaptation via Model Interpolation and Boosting for Web Search Ranking](https://mlsanity.com/paper/1907.09471/) (2019)

## Built on by (most cited first, 4 of 4)

- ["Why did the Model Fail?": Attributing Model Performance Changes to Distribution Shifts](https://mlsanity.com/paper/2210.10769/) (2022)
- [A hierarchical decomposition for explaining ML performance discrepancies](https://mlsanity.com/paper/2402.14254/) (2024)
- ["Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift](https://mlsanity.com/paper/2506.00756/) (2025)
- [ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values](https://mlsanity.com/paper/2604.11200/) (2026)

## Abstract (arXiv)

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.