# Out of Distribution Generalization in Machine Learning

arXiv: https://arxiv.org/abs/2103.02667 · HTML: https://mlsanity.com/paper/2103.02667/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2021.

## Built on by (most cited first, 30 of 60)

- [Goal Misgeneralization in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.14111/) (2021)
- [OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization](https://mlsanity.com/paper/2106.03721/) (2021)
- [Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning](https://mlsanity.com/paper/2503.07065/) (2025)
- [Dual-Personalizing Adapter for Federated Foundation Models](https://mlsanity.com/paper/2403.19211/) (2024)
- [Attention, please! A survey of Neural Attention Models in Deep Learning](https://mlsanity.com/paper/2103.16775/) (2021)
- [Out-of-distribution generalization for learning quantum dynamics](https://mlsanity.com/paper/2204.10268/) (2022)
- [Invariant Feature Learning for Generalized Long-Tailed Classification](https://mlsanity.com/paper/2207.09504/) (2022)
- [Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models](https://mlsanity.com/paper/2310.08106/) (2023)
- [Dangers of Bayesian Model Averaging under Covariate Shift](https://mlsanity.com/paper/2106.11905/) (2021)
- [Gradient Masked Averaging for Federated Learning](https://mlsanity.com/paper/2201.11986/) (2022)
- [Out-of-Distribution Generalization in Kernel Regression](https://mlsanity.com/paper/2106.02261/) (2021)
- [Masked Images Are Counterfactual Samples for Robust Fine-tuning](https://mlsanity.com/paper/2303.03052/) (2023)
- [Dimensionless machine learning: Imposing exact units equivariance](https://mlsanity.com/paper/2204.00887/) (2022)
- [Optimization-based Causal Estimation from Heterogenous Environments](https://mlsanity.com/paper/2109.11990/) (2021)
- [Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning](https://mlsanity.com/paper/2406.14302/) (2024)
- [When can in-context learning generalize out of task distribution?](https://mlsanity.com/paper/2506.05574/) (2025)
- [Meta-Causal Feature Learning for Out-of-Distribution Generalization](https://mlsanity.com/paper/2208.10156/) (2022)
- [Domain Generalisation via Imprecise Learning](https://mlsanity.com/paper/2404.04669/) (2024)
- [Subset verification and search algorithms for causal DAGs](https://mlsanity.com/paper/2301.03180/) (2023)
- [Integrating Reinforcement Learning with Visual Generative Models: Foundations and Advances](https://mlsanity.com/paper/2508.10316/) (2025)
- [Contrastive Learning of Generalized Game Representations](https://mlsanity.com/paper/2106.10060/) (2021)
- [Towards a theory of out-of-distribution learning](https://mlsanity.com/paper/2109.14501/) (2021)
- [On Invariance Penalties for Risk Minimization](https://mlsanity.com/paper/2106.09777/) (2021)
- [Bad Habits: Policy Confounding and Out-of-Trajectory Generalization in RL](https://mlsanity.com/paper/2306.02419/) (2023)
- [Group-Conditional Conformal Prediction via Quantile Regression Calibration for Crop and Weed Classification](https://mlsanity.com/paper/2308.15094/) (2023)
- [Neural Context Flows for Meta-Learning of Dynamical Systems](https://mlsanity.com/paper/2405.02154/) (2024)
- [When and How Does CLIP Enable Domain and Compositional Generalization?](https://mlsanity.com/paper/2502.09507/) (2025)
- [Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers](https://mlsanity.com/paper/2110.06990/) (2021)
- [Prospective Learning: Principled Extrapolation to the Future](https://mlsanity.com/paper/2201.07372/) (2022)
- [In Search of Deep Learning Architectures for Load Forecasting: A Comparative Analysis and the Impact of the Covid-19 Pandemic on Model Performance](https://mlsanity.com/paper/2302.13046/) (2023)

## Abstract (arXiv)

Machine learning has achieved tremendous success in a variety of domains in recent years. However, a lot of these success stories have been in places where the training and the testing distributions are extremely similar to each other. In everyday situations when models are tested in slightly different data than they were trained on, ML algorithms can fail spectacularly. This research attempts to formally define this problem, what sets of assumptions are reasonable to make in our data and what kind of guarantees we hope to obtain from them. Then, we focus on a certain class of out of distribution problems, their assumptions, and introduce simple algorithms that follow from these assumptions that are able to provide more reliable generalization. A central topic in the thesis is the strong link between discovering the causal structure of the data, finding features that are reliable (when using them to predict) regardless of their context, and out of distribution generalization.