# A New PAC-Bayesian Perspective on Domain Adaptation

arXiv: https://arxiv.org/abs/1506.04573 · HTML: https://mlsanity.com/paper/1506.04573/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2015.

## Built on by (most cited first, 29 of 29)

- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [User-friendly introduction to PAC-Bayes bounds](https://mlsanity.com/paper/2110.11216/) (2021)
- [Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand](https://mlsanity.com/paper/2310.14942/) (2023)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Invariant Learning via Probability of Sufficient and Necessary Causes](https://mlsanity.com/paper/2309.12559/) (2023)
- [Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning](https://mlsanity.com/paper/2105.14099/) (2021)
- [The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalization](https://mlsanity.com/paper/2204.04384/) (2022)
- [Position: Understanding LLMs Requires More Than Statistical Generalization](https://mlsanity.com/paper/2405.01964/) (2024)
- [Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithm](https://mlsanity.com/paper/2111.01635/) (2021)
- [Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Features](https://mlsanity.com/paper/2111.03740/) (2021)
- [PAC-Bayesian Domain Adaptation Bounds for Multiclass Learners](https://mlsanity.com/paper/2207.05685/) (2022)
- [Towards Robust Out-of-Distribution Generalization Bounds via Sharpness](https://mlsanity.com/paper/2403.06392/) (2024)
- [On f-Divergence Principled Domain Adaptation: An Improved Framework](https://mlsanity.com/paper/2402.01887/) (2024)
- [Phase-driven Domain Generalizable Learning for Nonstationary Time Series](https://mlsanity.com/paper/2402.05960/) (2024)
- [PAC-Bayesian Lifelong Learning For Multi-Armed Bandits](https://mlsanity.com/paper/2203.03303/) (2022)
- [On Label Shift in Domain Adaptation via Wasserstein Distance](https://mlsanity.com/paper/2110.15520/) (2021)
- [CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift](https://mlsanity.com/paper/2305.18458/) (2023)
- [Out-Of-Domain Unlabeled Data Improves Generalization](https://mlsanity.com/paper/2310.00027/) (2023)
- [Bayesian Transfer Learning](https://mlsanity.com/paper/2312.13484/) (2023)
- [Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis](https://mlsanity.com/paper/2405.09516/) (2024)
- [Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localization](https://mlsanity.com/paper/2203.05076/) (2022)
- [PAC-Bayesian Domain Adaptation Bounds for Multi-view learning](https://mlsanity.com/paper/2401.01048/) (2024)
- [On the inductive biases of deep domain adaptation](https://mlsanity.com/paper/2109.07920/) (2021)
- [Practicality of generalization guarantees for unsupervised domain adaptation with neural networks](https://mlsanity.com/paper/2303.08720/) (2023)
- [ODD: Overlap-aware Estimation of Model Performance under Distribution Shift](https://mlsanity.com/paper/2506.14978/) (2025)
- [Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Data](https://mlsanity.com/paper/2311.18758/) (2023)
- [STAMP: Symmetric Temporal Averaging Message Passing for Domain Adaptation in Chronologically Split Graphs](https://mlsanity.com/paper/2411.10957/) (2024)
- [Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiency](https://mlsanity.com/paper/2508.18693/) (2025)
- [TRACE: Theoretical Risk Attribution under Covariate-shift Effects](https://mlsanity.com/paper/2602.10588/) (2026)

## Abstract (arXiv)

We study the issue of PAC-Bayesian domain adaptation: We want to learn, from a source domain, a majority vote model dedicated to a target one. Our theoretical contribution brings a new perspective by deriving an upper-bound on the target risk where the distributions' divergence---expressed as a ratio---controls the trade-off between a source error measure and the target voters' disagreement. Our bound suggests that one has to focus on regions where the source data is informative.From this result, we derive a PAC-Bayesian generalization bound, and specialize it to linear classifiers. Then, we infer a learning algorithmand perform experiments on real data.