mlsanityData to 7 Oct 2026

On f-Divergence Principled Domain Adaptation: An Improved Framework

arXiv 2402.01887 ↗First posted 2 Feb 2024stat.ML cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Unsupervised domain adaptation (UDA) plays a crucial role in addressing distribution shifts in machine learning. In this work, we improve the theoretical foundations of UDA proposed in Acuna et al. (2021) by refining their f-divergence-based discrepancy and additionally introducing a new measure, f-domain discrepancy (f-DD). By removing the absolute value function and incorporating a scaling parameter, f-DD obtains novel target error and sample complexity bounds, allowing us to recover previous KL-based results and bridging the gap between algorithms and theory presented in Acuna et al. (2021). Using a localization technique, we also develop a fast-rate generalization bound. Empirical results demonstrate the superior performance of f-DD-based learning algorithms over previous works in popular UDA benchmarks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 79 references that are in the map. First posted on arXiv 2 Feb 2024.

Builds on

38 of 79 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  6. 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
  7. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  8. 2015Optimal Transport for Domain Adaptationcited by 457
  9. 2015Return of Frustratingly Easy Domain Adaptationcited by 389
  10. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  11. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  12. 2017Joint Distribution Optimal Transportation for Domain Adaptationcited by 280
26 more
  1. 2021User-friendly introduction to PAC-Bayes boundscited by 234
  2. 2020A survey on domain adaptation theory: learning bounds and theoretical guaranteescited by 109
  3. 2019On the Existence of Simpler Machine Learning Modelscited by 87
  4. 2020On the Value of Target Data in Transfer Learningcited by 62
  5. 2019Domain Adaptation with Asymmetrically-Relaxed Distribution Alignmentcited by 61
  6. 2022Safe Self-Refinement for Transformer-based Domain Adaptationcited by 61
  7. 2020Implicit Class-Conditioned Domain Alignment for Unsupervised Domain Adaptationcited by 60
  8. 2023Patch-Mix Transformer for Unsupervised Domain Adaptation: A Game Perspectivecited by 54
  9. 2021f-Domain-Adversarial Learning: Theory and Algorithmscited by 47
  10. 2021KL Guided Domain Adaptationcited by 35
  11. 2015A New PAC-Bayesian Perspective on Domain Adaptationcited by 29
  12. 2022A New Family of Generalization Bounds Using Samplewise Evaluated CMIcited by 28
  13. 2020Optimal Bounds between f-Divergences and Integral Probability Metricscited by 27
  14. 2019Bridging the Gap Between f-GANs and Wasserstein GANscited by 23
  15. 2020Information-theoretic analysis for transfer learningcited by 23
  16. 2023Tighter Information-Theoretic Generalization Bounds from Supersamplescited by 21
  17. 2019Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processescited by 20
  18. 2020Optimizing Variational Representations of Divergences and Accelerating their Statistical Estimationcited by 15
  19. 2022Information-Theoretic Analysis of Unsupervised Domain Adaptationcited by 15
  20. 2021Characterizing and Understanding the Generalization Error of Transfer Learning with Gibbs Algorithmcited by 14
  21. 2020On Localized Discrepancy for Domain Adaptationcited by 13
  22. 2014Adaptation Algorithm and Theory Based on Generalized Discrepancycited by 9
  23. 2023Limits of Model Selection under Transfer Learningcited by 9
  24. 2020On the Theoretical Equivalence of Several Trade-Off Curves Assessing Statistical Proximitycited by 6
  25. 2023Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Boundscited by 5
  26. 2022Connecting sufficient conditions for domain adaptation: source-guided uncertainty, relaxed divergences and discrepancy localizationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2025Domain Adaptation and Entanglement: an Optimal Transport Perspectivecited by 6
  2. 2024Generalization Bounds via Conditional f-Informationcited by 3
  3. 2025On the Hardness of Unsupervised Domain Adaptation: Optimal Learners and Information-Theoretic Perspectivecited by 1
  4. 2025Seeking Flat Minima over Diverse Surrogates for Improved Adversarial Transferability: A Theoretical Framework and Algorithmic Instantiationcited by 0
  5. 2025An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learningcited by 0
  6. 2026Autonomous Drift Learning in Data Streams: A Unified Perspectivecited by 0