mlsanityData to 14 Oct 2026

Adaptive transfer learning

arXiv 2106.04455 ↗First posted 8 Jun 2021stat.ML cs.LG math.STcited by 4

Not on the map. Why?

Abstract (arXiv)

In transfer learning, we wish to make inference about a target population when we have access to data both from the distribution itself, and from a different but related source distribution. We introduce a flexible framework for transfer learning in the context of binary classification, allowing for covariate-dependent relationships between the source and target distributions that are not required to preserve the Bayes decision boundary. Our main contributions are to derive the minimax optimal rates of convergence (up to poly-logarithmic factors) in this problem, and show that the optimal rate can be achieved by an algorithm that adapts to key aspects of the unknown transfer relationship, as well as the smoothness and tail parameters of our distributional classes. This optimal rate turns out to have several regimes, depending on the interplay between the relative sample sizes and the strength of the transfer relationship, and our algorithm achieves optimality by careful, decision tree-based calibration of local nearest-neighbour procedures.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 20 of its 70 references that are in the map. First posted on arXiv 8 Jun 2021.

Builds on

20 of 70 references.

References · 20

  1. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  2. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  3. 2015The Benefit of Multitask Representation Learningcited by 195
  4. 2017Domain Generalization by Marginal Transfer Learningcited by 180
  5. 2013Classification with Asymmetric Label Noise: Consistency and Maximal Denoisingcited by 68
  6. 2018Marginal Singularity, and the Benefits of Labels in Covariate-Shiftcited by 65
  7. 2019Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifiercited by 65
  8. 2020On the Value of Target Data in Transfer Learningcited by 65
  9. 2015Risk Bounds for the Majority Vote: From a PAC-Bayesian Analysis to a Learning Algorithmcited by 50
  10. 2014Rates of Convergence for Nearest Neighbor Classificationcited by 46
  11. 2018A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptationcited by 23
  12. 2020Minimax optimal approaches to the label shift problem in non-parametric settingscited by 20
8 more
  1. 2017Local nearest neighbour classification with applications to semi-supervised learningcited by 17
  2. 2017Recent progress in log-concave density estimationcited by 15
  3. 2019Fast Rates for a kNN Classifier Robust to Unknown Asymmetric Label Noisecited by 11
  4. 2019Classification with unknown class-conditional label noise on non-compact feature spacescited by 9
  5. 2019Learning from Multiple Corrupted Sources, with Application to Learning from Label Proportionscited by 4
  6. 2018Minimax rates for cost-sensitive learning on manifolds with approximate nearest neighbourscited by 3
  7. 2013Cellular Tree Classifierscited by 1
  8. 2020Causality in cognitive neuroscience: concepts, challenges, and distributional robustnesscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 0; 2026: 1.

4 papers.

  1. 2023Model-free Test Time Adaptation for Out-Of-Distribution Detectioncited by 9
  2. 2022Transfer Learning with Uncertainty Quantification: Random Effect Calibration of Source to Target (RECaST)cited by 6
  3. 2024Minimax And Adaptive Transfer Learning for Nonparametric Classification under Distributed Differential Privacy Constraintscited by 5
  4. 2026Personalizing black-box models for nonparametric regression with minimax optimalitycited by 0