# A survey on domain adaptation theory: learning bounds and theoretical guarantees

arXiv: https://arxiv.org/abs/2004.11829 · HTML: https://mlsanity.com/paper/2004.11829/

## Key facts

- Cited by 109 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 30 of 109)

- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Does Invariant Risk Minimization Capture Invariance?](https://mlsanity.com/paper/2101.01134/) (2021)
- [Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift](https://mlsanity.com/paper/2206.13089/) (2022)
- [Generalization on the Unseen, Logic Reasoning and Degree Curriculum](https://mlsanity.com/paper/2301.13105/) (2023)
- [Transferability in Deep Learning: A Survey](https://mlsanity.com/paper/2201.05867/) (2022)
- [Specificity-Preserving Federated Learning for MR Image Reconstruction](https://mlsanity.com/paper/2112.05752/) (2021)
- [A System-Level View on Out-of-Distribution Data in Robotics](https://mlsanity.com/paper/2212.14020/) (2022)
- [Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs](https://mlsanity.com/paper/2405.02774/) (2024)
- [Credal Learning Theory](https://mlsanity.com/paper/2402.00957/) (2024)
- [DARE-GRAM : Unsupervised Domain Adaptation Regression by Aligning Inverse Gram Matrices](https://mlsanity.com/paper/2303.13325/) (2023)
- [Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey](https://mlsanity.com/paper/2305.05080/) (2023)
- [Probabilistically robust conformal prediction](https://mlsanity.com/paper/2307.16360/) (2023)
- [Testable Learning with Distribution Shift](https://mlsanity.com/paper/2311.15142/) (2023)
- [Robustness Implies Generalization via Data-Dependent Generalization Bounds](https://mlsanity.com/paper/2206.13497/) (2022)
- [DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization](https://mlsanity.com/paper/2308.10285/) (2023)
- [Lifelong Teacher-Student Network Learning](https://mlsanity.com/paper/2107.04689/) (2021)
- [Towards Robust Graph Incremental Learning on Evolving Graphs](https://mlsanity.com/paper/2402.12987/) (2024)
- [A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks](https://mlsanity.com/paper/2305.17040/) (2023)
- [Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNs](https://mlsanity.com/paper/2406.15156/) (2024)
- [Information-Theoretic Analysis of Unsupervised Domain Adaptation](https://mlsanity.com/paper/2210.00706/) (2022)
- [Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time](https://mlsanity.com/paper/2306.04255/) (2023)
- [Tolerant Algorithms for Learning with Arbitrary Covariate Shift](https://mlsanity.com/paper/2406.02742/) (2024)
- [PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners](https://mlsanity.com/paper/2207.05685/) (2022)
- [Learning Intersections of Halfspaces with Distribution Shift: Improved Algorithms and SQ Lower Bounds](https://mlsanity.com/paper/2404.02364/) (2024)
- [The Change that Matters in Discourse Parsing: Estimating the Impact of Domain Shift on Parser Error](https://mlsanity.com/paper/2203.11317/) (2022)
- [Multi-Source Domain Adaptation through Dataset Dictionary Learning in Wasserstein Space](https://mlsanity.com/paper/2307.14953/) (2023)
- [Gradual Domain Adaptation via Normalizing Flows](https://mlsanity.com/paper/2206.11492/) (2022)
- [Measuring the Robustness of NLP Models to Domain Shifts](https://mlsanity.com/paper/2306.00168/) (2023)

## Abstract (arXiv)

All famous machine learning algorithms that comprise both supervised and semi-supervised learning work well only under a common assumption: the training and test data follow the same distribution. When the distribution changes, most statistical models must be reconstructed from newly collected data, which for some applications can be costly or impossible to obtain. Therefore, it has become necessary to develop approaches that reduce the need and the effort to obtain new labeled samples by exploiting data that are available in related areas, and using these further across similar fields. This has given rise to a new machine learning framework known as transfer learning: a learning setting inspired by the capability of a human being to extrapolate knowledge across tasks to learn more efficiently. Despite a large amount of different transfer learning scenarios, the main objective of this survey is to provide an overview of the state-of-the-art theoretical results in a specific, and arguably the most popular, sub-field of transfer learning, called domain adaptation. In this sub-field, the data distribution is assumed to change across the training and the test data, while the learning task remains the same. We provide a first up-to-date description of existing results related to domain adaptation problem that cover learning bounds based on different statistical learning frameworks.