# Diagnosing Model Performance Under Distribution Shift

arXiv: https://arxiv.org/abs/2303.02011 · HTML: https://mlsanity.com/paper/2303.02011/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 119 references that are in the map.
- First posted on arXiv 3 Mar 2023.

## Builds on (most cited first, 30 of 46)

- [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [WILDS: A Benchmark of in-the-Wild Distribution Shifts](https://mlsanity.com/paper/2012.07421/) (2020)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Causal inference using invariant prediction: identification and confidence intervals](https://mlsanity.com/paper/1501.01332/) (2015)
- [Measuring Robustness to Natural Distribution Shifts in Image Classification](https://mlsanity.com/paper/2007.00644/) (2020)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [Functional Map of the World](https://mlsanity.com/paper/1711.07846/) (2017)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [The Risks of Invariant Risk Minimization](https://mlsanity.com/paper/2010.05761/) (2020)
- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learning](https://mlsanity.com/paper/1908.08729/) (2019)
- [Semiparametric doubly robust targeted double machine learning: a review](https://mlsanity.com/paper/2203.06469/) (2022)
- [Distributionally Robust Logistic Regression](https://mlsanity.com/paper/1509.09259/) (2015)
- [Anchor regression: heterogeneous data meets causality](https://mlsanity.com/paper/1801.06229/) (2018)
- [Ethical Machine Learning in Health Care](https://mlsanity.com/paper/2009.10576/) (2020)
- [The Effect of Natural Distribution Shift on Question Answering Models](https://mlsanity.com/paper/2004.14444/) (2020)
- [Plex: Towards Reliability using Pretrained Large Model Extensions](https://mlsanity.com/paper/2207.07411/) (2022)
- [The iWildCam 2020 Competition Dataset](https://mlsanity.com/paper/2004.10340/) (2020)
- [Extending the WILDS Benchmark for Unsupervised Adaptation](https://mlsanity.com/paper/2112.05090/) (2021)
- [Data-Driven Robust Optimization](https://mlsanity.com/paper/1401.0212/) (2013)
- [Confounding-Robust Policy Improvement](https://mlsanity.com/paper/1805.08593/) (2018)
- [Distributionally Robust Optimization and Generalization in Kernel Methods](https://mlsanity.com/paper/1905.10943/) (2019)
- [Balancing Covariates via Propensity Score Weighting](https://mlsanity.com/paper/1609.07494/) (2016)
- [Distributional Smoothing with Virtual Adversarial Training](https://mlsanity.com/paper/1507.00677/) (2015)

## Built on by (most cited first, 30 of 39)

- [MuggleMath: Assessing the Impact of Query and Response Augmentation on Math Reasoning](https://mlsanity.com/paper/2310.05506/) (2023)
- [A Survey on Evaluation of Out-of-Distribution Generalization](https://mlsanity.com/paper/2403.01874/) (2024)
- [A Baseline Analysis of Reward Models' Ability To Accurately Analyze Foundation Models Under Distribution Shift](https://mlsanity.com/paper/2311.14743/) (2023)
- [The Data Addition Dilemma](https://mlsanity.com/paper/2408.04154/) (2024)
- [Multi-Source Conformal Inference Under Distribution Shift](https://mlsanity.com/paper/2405.09331/) (2024)
- [DAFNet: Dynamic Auxiliary Fusion for Sequential Model Editing in Large Language Models](https://mlsanity.com/paper/2405.20588/) (2024)
- [Understanding Disparities in Post Hoc Machine Learning Explanation](https://mlsanity.com/paper/2401.14539/) (2024)
- [Distributionally Robust Policy Learning under Concept Drifts](https://mlsanity.com/paper/2412.14297/) (2024)
- [Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness](https://mlsanity.com/paper/2506.04193/) (2025)
- [A hierarchical decomposition for explaining ML performance discrepancies](https://mlsanity.com/paper/2402.14254/) (2024)
- [Beyond Reweighting: On the Predictive Role of Covariate Shift in Effect Generalization](https://mlsanity.com/paper/2412.08869/) (2024)
- [Realistic Evaluation of TabPFN v2 in Open Environments](https://mlsanity.com/paper/2505.16226/) (2025)
- [Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning](https://mlsanity.com/paper/2508.04329/) (2025)
- [Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation](https://mlsanity.com/paper/2601.21315/) (2026)
- [LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shifts](https://mlsanity.com/paper/2410.07395/) (2024)
- [Robust prediction under missingness shifts](https://mlsanity.com/paper/2406.16484/) (2024)
- [Adaptive Estimation and Learning under Temporal Distribution Shift](https://mlsanity.com/paper/2505.15803/) (2025)
- [A Directional Rockafellar-Uryasev Regression](https://mlsanity.com/paper/2411.02557/) (2024)
- ["Who experiences large model decay and why?" A Hierarchical Framework for Diagnosing Heterogeneous Performance Drift](https://mlsanity.com/paper/2506.00756/) (2025)
- [Structured Credal Learning](https://mlsanity.com/paper/2603.14070/) (2026)
- [Beyond the Training Distribution: Evaluating Predictions Under Distribution Shift and Selection Bias](https://mlsanity.com/paper/2606.14506/) (2026)
- [When Can You Trust Your Synthetic Users? Diagnostics and Corrections for LLM Consumer Panels](https://mlsanity.com/paper/2609.13148/) (2026)
- [Structure-agnostic Causal Representation Learning](https://mlsanity.com/paper/2610.00968/) (2026)
- [Label Shift Estimators for Non-Ignorable Missing Data](https://mlsanity.com/paper/2310.18261/) (2023)
- [A robust assessment for invariant representations](https://mlsanity.com/paper/2404.05058/) (2024)
- [Fairness Hub Technical Briefs: Definition and Detection of Distribution Shift](https://mlsanity.com/paper/2405.14186/) (2024)
- [Control+Shift: Generating Controllable Distribution Shifts](https://mlsanity.com/paper/2409.07940/) (2024)
- [Explaining Concept Shift with Interpretable Feature Attribution](https://mlsanity.com/paper/2505.20634/) (2025)
- [Data Heterogeneity Modeling for Trustworthy Machine Learning](https://mlsanity.com/paper/2506.00969/) (2025)
- [Uncovering Bias Mechanisms in Observational Studies](https://mlsanity.com/paper/2506.01191/) (2025)

## Abstract (arXiv)

Prediction models can perform poorly when deployed to target distributions different from the training distribution. To understand these operational failure modes, we develop a method, called DIstribution Shift DEcomposition (DISDE), to attribute a drop in performance to different types of distribution shifts. Our approach decomposes the performance drop into terms for 1) an increase in harder but frequently seen examples from training, 2) changes in the relationship between features and outcomes, and 3) poor performance on examples infrequent or unseen during training. These terms are defined by fixing a distribution on X while varying the conditional distribution of Y mid X between training and target, or by fixing the conditional distribution of Y mid X while varying the distribution on X. In order to do this, we define a hypothetical distribution on X consisting of values common in both training and target, over which it is easy to compare Y mid X and thus predictive performance. We estimate performance on this hypothetical distribution via reweighting methods. Empirically, we show how our method can 1) inform potential modeling improvements across distribution shifts for employment prediction on tabular census data, and 2) help to explain why certain domain adaptation methods fail to improve model performance for satellite image classification.