DeepAI AI Chat
Log In Sign Up

Leveraging Unlabeled Data to Predict Out-of-Distribution Performance

by   Saurabh Garg, et al.

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.


page 1

page 2

page 3

page 4


Test-time Recalibration of Conformal Predictors Under Distribution Shift Based on Unlabeled Examples

Modern image classifiers achieve high predictive accuracy, but the predi...

Regularized Learning for Domain Adaptation under Label Shifts

We propose Regularized Learning under Label shifts (RLLS), a principled ...

NURD: Negative-Unlabeled Learning for Online Datacenter Straggler Prediction

Datacenters execute large computational jobs, which are composed of smal...

Distributionally Robust Data Join

Suppose we are given two datasets: a labeled dataset and unlabeled datas...

Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift

Recently, Miller et al. showed that a model's in-distribution (ID) accur...

Extending the WILDS Benchmark for Unsupervised Adaptation

Machine learning systems deployed in the wild are often trained on a sou...

Mandoline: Model Evaluation under Distribution Shift

Machine learning models are often deployed in different settings than th...