# Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

arXiv: https://arxiv.org/abs/2201.04234 · HTML: https://mlsanity.com/paper/2201.04234/

## Key facts

- Cited by 145 papers in the map (data through 14 Oct 2026).
- Builds on 51 of its 85 references that are in the map.
- First posted on arXiv 11 Jan 2022.

## Builds on (most cited first, 30 of 51)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization](https://mlsanity.com/paper/2006.16241/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [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)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Selective Classification for Deep Neural Networks](https://mlsanity.com/paper/1705.08500/) (2017)
- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [Exploring Generalization in Deep Learning](https://mlsanity.com/paper/1706.08947/) (2017)
- [Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data](https://mlsanity.com/paper/1703.11008/) (2017)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [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)
- [Norm-Based Capacity Control in Neural Networks](https://mlsanity.com/paper/1503.00036/) (2015)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Uniform convergence may be unable to explain generalization in deep learning](https://mlsanity.com/paper/1902.04742/) (2019)
- [To Trust Or Not To Trust A Classifier](https://mlsanity.com/paper/1805.11783/) (2018)

## Built on by (most cited first, 30 of 145)

- [Large Language Model Routing with Benchmark Datasets](https://mlsanity.com/paper/2309.15789/) (2023)
- [Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift](https://mlsanity.com/paper/2206.13089/) (2022)
- [AutoEval Done Right: Using Synthetic Data for Model Evaluation](https://mlsanity.com/paper/2403.07008/) (2024)
- [RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection](https://mlsanity.com/paper/2209.08590/) (2022)
- [Predicting Out-of-Distribution Error with the Projection Norm](https://mlsanity.com/paper/2202.05834/) (2022)
- [Domain Adaptation under Open Set Label Shift](https://mlsanity.com/paper/2207.13048/) (2022)
- [Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data](https://mlsanity.com/paper/2310.16524/) (2023)
- [RLSbench: Domain Adaptation Under Relaxed Label Shift](https://mlsanity.com/paper/2302.03020/) (2023)
- [The Entropy Enigma: Success and Failure of Entropy Minimization](https://mlsanity.com/paper/2405.05012/) (2024)
- [On the Strong Correlation Between Model Invariance and Generalization](https://mlsanity.com/paper/2207.07065/) (2022)
- [What Do Learning Dynamics Reveal About Generalization in LLM Reasoning?](https://mlsanity.com/paper/2411.07681/) (2024)
- [Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimation](https://mlsanity.com/paper/2302.01094/) (2023)
- [A Survey on Evaluation of Out-of-Distribution Generalization](https://mlsanity.com/paper/2403.01874/) (2024)
- [Characterizing Out-of-Distribution Error via Optimal Transport](https://mlsanity.com/paper/2305.15640/) (2023)
- [Deconstructing Distributions: A Pointwise Framework of Learning](https://mlsanity.com/paper/2202.09931/) (2022)
- [Estimating and Explaining Model Performance When Both Covariates and Labels Shift](https://mlsanity.com/paper/2209.08436/) (2022)
- [A Learning Based Hypothesis Test for Harmful Covariate Shift](https://mlsanity.com/paper/2212.02742/) (2022)
- [GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels](https://mlsanity.com/paper/2310.14586/) (2023)
- [Energy-based Automated Model Evaluation](https://mlsanity.com/paper/2401.12689/) (2024)
- [A Note on "Assessing Generalization of SGD via Disagreement"](https://mlsanity.com/paper/2202.01851/) (2022)
- [(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy](https://mlsanity.com/paper/2306.00312/) (2023)
- [On the Importance of Feature Separability in Predicting Out-Of-Distribution Error](https://mlsanity.com/paper/2303.15488/) (2023)
- [Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?](https://mlsanity.com/paper/2305.18712/) (2023)
- [A Framework for Efficient Model Evaluation through Stratification, Sampling, and Estimation](https://mlsanity.com/paper/2406.07320/) (2024)
- [Predicting Out-of-Distribution Error with Confidence Optimal Transport](https://mlsanity.com/paper/2302.05018/) (2023)
- [Demystifying Disagreement-on-the-Line in High Dimensions](https://mlsanity.com/paper/2301.13371/) (2023)
- [CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis](https://mlsanity.com/paper/2310.04414/) (2023)
- [Online GNN Evaluation Under Test-time Graph Distribution Shifts](https://mlsanity.com/paper/2403.09953/) (2024)
- [Understanding new tasks through the lens of training data via exponential tilting](https://mlsanity.com/paper/2205.13577/) (2022)
- [A Bag-of-Prototypes Representation for Dataset-Level Applications](https://mlsanity.com/paper/2303.13251/) (2023)

## Abstract (arXiv)

Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions that may cause performance drops. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples for which model confidence exceeds that threshold. ATC outperforms previous methods across several model architectures, types of distribution shifts (e.g., due to synthetic corruptions, dataset reproduction, or novel subpopulations), and datasets (Wilds, ImageNet, Breeds, CIFAR, and MNIST). In our experiments, ATC estimates target performance 2-4× more accurately than prior methods. We also explore the theoretical foundations of the problem, proving that, in general, identifying the accuracy is just as hard as identifying the optimal predictor and thus, the efficacy of any method rests upon (perhaps unstated) assumptions on the nature of the shift. Finally, analyzing our method on some toy distributions, we provide insights concerning when it works. Code is available at https://github.com/saurabhgarg1996/ATCcode/.