# Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift

arXiv: https://arxiv.org/abs/2207.08977 · HTML: https://mlsanity.com/paper/2207.08977/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Builds on 47 of its 77 references that are in the map.
- First posted on arXiv 18 Jul 2022.

## Builds on (most cited first, 30 of 47)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [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)
- [Moment Matching for Multi-Source Domain Adaptation](https://mlsanity.com/paper/1812.01754/) (2018)
- [Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift](https://mlsanity.com/paper/1906.02530/) (2019)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [In Search of Lost Domain Generalization](https://mlsanity.com/paper/2007.01434/) (2020)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Robust fine-tuning of zero-shot models](https://mlsanity.com/paper/2109.01903/) (2021)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [Just Train Twice: Improving Group Robustness without Training Group Information](https://mlsanity.com/paper/2107.09044/) (2021)
- [Unlabeled Data Improves Adversarial Robustness](https://mlsanity.com/paper/1905.13736/) (2019)
- [Nuanced Metrics for Measuring Unintended Bias with Real Data for Text Classification](https://mlsanity.com/paper/1903.04561/) (2019)
- [Confounding variables can degrade generalization performance of radiological deep learning models](https://mlsanity.com/paper/1807.00431/) (2018)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [Fairness Without Demographics in Repeated Loss Minimization](https://mlsanity.com/paper/1806.08010/) (2018)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [Calibration of Pre-trained Transformers](https://mlsanity.com/paper/2003.07892/) (2020)
- [An Investigation of Why Overparameterization Exacerbates Spurious Correlations](https://mlsanity.com/paper/2005.04345/) (2020)

## Built on by (most cited first, 30 of 34)

- [Finetune like you pretrain: Improved finetuning of zero-shot vision models](https://mlsanity.com/paper/2212.00638/) (2022)
- [A Close Look into the Calibration of Pre-trained Language Models](https://mlsanity.com/paper/2211.00151/) (2022)
- [Towards Calibrated Robust Fine-Tuning of Vision-Language Models](https://mlsanity.com/paper/2311.01723/) (2023)
- [Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models](https://mlsanity.com/paper/2310.08106/) (2023)
- [Spurious Feature Diversification Improves Out-of-distribution Generalization](https://mlsanity.com/paper/2309.17230/) (2023)
- [Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting](https://mlsanity.com/paper/2410.19294/) (2024)
- [It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition](https://mlsanity.com/paper/2402.05457/) (2024)
- [Gaussian Stochastic Weight Averaging for Bayesian Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2405.03425/) (2024)
- [Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothing](https://mlsanity.com/paper/2301.12554/) (2023)
- [Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition](https://mlsanity.com/paper/2308.09694/) (2023)
- [FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning](https://mlsanity.com/paper/2310.15105/) (2023)
- [Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement](https://mlsanity.com/paper/2303.08983/) (2023)
- [Classes Are Not Equal: An Empirical Study on Image Recognition Fairness](https://mlsanity.com/paper/2402.18133/) (2024)
- [Controllable Prompt Tuning For Balancing Group Distributional Robustness](https://mlsanity.com/paper/2403.02695/) (2024)
- [Understanding Overadaptation in Supervised Fine-Tuning: The Role of Ensemble Methods](https://mlsanity.com/paper/2506.01901/) (2025)
- [On the Benefits of Over-parameterization for Out-of-Distribution Generalization](https://mlsanity.com/paper/2403.17592/) (2024)
- [Malign Overfitting: Interpolation Can Provably Preclude Invariance](https://mlsanity.com/paper/2211.15724/) (2022)
- [Robust Fine-tuning of Zero-shot Models via Variance Reduction](https://mlsanity.com/paper/2411.06966/) (2024)
- [LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views](https://mlsanity.com/paper/2402.04644/) (2024)
- [Where are we with calibration under dataset shift in image classification?](https://mlsanity.com/paper/2507.07780/) (2025)
- [Reweighted Mixup for Subpopulation Shift](https://mlsanity.com/paper/2304.04148/) (2023)
- [Bridging Domains with Approximately Shared Features](https://mlsanity.com/paper/2403.06424/) (2024)
- [Beyond Accuracy: On the Effects of Fine-tuning Towards Vision-Language Model's Prediction Rationality](https://mlsanity.com/paper/2412.13333/) (2024)
- [Variance-Gated Ensembles: An Epistemic-Aware Framework for Uncertainty Estimation](https://mlsanity.com/paper/2602.08142/) (2026)
- [QuantProb: Generalizing Probabilities along with Predictions for a Pre-trained Classifier](https://mlsanity.com/paper/2304.12766/) (2023)
- [Assessing Uncertainty Estimation Methods for 3D Image Segmentation under Distribution Shifts](https://mlsanity.com/paper/2402.06937/) (2024)
- [Predicate Debiasing in Vision-Language Models Integration for Scene Graph Generation Enhancement](https://mlsanity.com/paper/2403.16184/) (2024)
- [Integrating uncertainty quantification into randomized smoothing based robustness guarantees](https://mlsanity.com/paper/2410.20432/) (2024)
- [TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models](https://mlsanity.com/paper/2511.16423/) (2025)
- [Missingness Bias Calibration in Feature Attribution Explanations](https://mlsanity.com/paper/2603.04831/) (2026)

## Abstract (arXiv)

We often see undesirable tradeoffs in robust machine learning where out-of-distribution (OOD) accuracy is at odds with in-distribution (ID) accuracy: a robust classifier obtained via specialized techniques such as removing spurious features often has better OOD but worse ID accuracy compared to a standard classifier trained via ERM. In this paper, we find that ID-calibrated ensembles -- where we simply ensemble the standard and robust models after calibrating on only ID data -- outperforms prior state-of-the-art (based on self-training) on both ID and OOD accuracy. On eleven natural distribution shift datasets, ID-calibrated ensembles obtain the best of both worlds: strong ID accuracy and OOD accuracy. We analyze this method in stylized settings, and identify two important conditions for ensembles to perform well both ID and OOD: (1) we need to calibrate the standard and robust models (on ID data, because OOD data is unavailable), (2) OOD has no anticorrelated spurious features.