mlsanityData to 7 Oct 2026

A New PAC-Bayesian Perspective on Domain Adaptation

arXiv 1506.04573 ↗First posted 15 Jun 2015stat.ML cs.LGcited by 29

Not on the map. Why?

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.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 4; 2023: 8; 2024: 7; 2025: 2; 2026: 1.

29 papers.

Sort:

By area:

  1. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  2. 2021User-friendly introduction to PAC-Bayes boundscited by 234
  3. 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Handcited by 52
  4. 2023Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectivescited by 30
  5. 2023Invariant Learning via Probability of Sufficient and Necessary Causescited by 22
  6. 2021Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learningcited by 21
  7. 2022The Two Dimensions of Worst-case Training and the Integrated Effect for Out-of-domain Generalizationcited by 21
  8. 2024Position: Understanding LLMs Requires More Than Statistical Generalizationcited by 20
  9. 2021Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithmcited by 14
  10. 2021Toward Learning Human-aligned Cross-domain Robust Models by Countering Misaligned Featurescited by 14
  11. 2022PAC-Bayesian Domain Adaptation Bounds for Multiclass Learnerscited by 13
  12. 2024Towards Robust Out-of-Distribution Generalization Bounds via Sharpnesscited by 10
17 more
  1. 2024On f-Divergence Principled Domain Adaptation: An Improved Frameworkcited by 6
  2. 2022PAC-Bayesian Lifelong Learning For Multi-Armed Banditscited by 4
  3. 2024Phase-driven Domain Generalizable Learning for Nonstationary Time Seriescited by 4
  4. 2023CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shiftcited by 3
  5. 2023Out-Of-Domain Unlabeled Data Improves Generalizationcited by 3
  6. 2023Bayesian Transfer Learningcited by 3
  7. 2024Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysiscited by 3
  8. 2021On Label Shift in Domain Adaptation via Wasserstein Distancecited by 2
  9. 2022Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localizationcited by 2
  10. 2021On the inductive biases of deep domain adaptationcited by 1
  11. 2023Practicality of generalization guarantees for unsupervised domain adaptation with neural networkscited by 1
  12. 2024PAC-Bayesian Domain Adaptation Bounds for Multi-view learningcited by 1
  13. 2025ODD: Overlap-aware Estimation of Model Performance under Distribution Shiftcited by 1
  14. 2023Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Datacited by 0
  15. 2024IMPaCT GNN: Imposing invariance with Message Passing in Chronological split Temporal Graphscited by 0
  16. 2025Feature-Space Planes Searcher: A Universal Domain Adaptation Framework for Interpretability and Computational Efficiencycited by 0
  17. 2026TRACE: Theoretical Risk Attribution under Covariate-shift Effectscited by 0