mlsanityData to 14 Oct 2026

Sequential Domain Adaptation by Synthesizing Distributionally Robust Experts

arXiv 2106.00322 ↗First posted 1 Jun 2021cs.LG math.OC stat.MLcited by 14

Not on the map. Why?

Abstract (arXiv)

Least squares estimators, when trained on a few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a source distribution that is close to the target distribution. Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions. When these moment conditions are specified using Kullback-Leibler or Wasserstein-type divergences, we can find the robust estimators efficiently using convex optimization. We use the Bernstein online aggregation algorithm on the proposed family of robust experts to generate predictions for the sequential stream of target test samples. Numerical experiments on real data show that the robust strategies may outperform non-robust interpolations of the empirical least squares estimators.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 27 of its 74 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

27 of 74 references.

References · 27

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,917
  2. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  3. 2015Optimal Transport for Domain Adaptationcited by 463
  4. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 366
  5. 2018A Survey of Unsupervised Deep Domain Adaptationcited by 361
  6. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  7. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  8. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  9. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 291
  10. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  11. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 170
  12. 2016Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptationcited by 163
15 more
  1. 2019Regularized Learning for Domain Adaptation under Label Shiftscited by 120
  2. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  3. 2019Adaptive Gradient Descent without Descentcited by 79
  4. 2018A Survey of Domain Adaptation for Neural Machine Translationcited by 64
  5. 2020Finite-Sample Guarantees for Wasserstein Distributionally Robust Optimization: Breaking the Curse of Dimensionalitycited by 49
  6. 2014Optimal learning with Bernstein Online Aggregationcited by 35
  7. 2016Recovering Best Statistical Guarantees via the Empirical Divergence-based Distributionally Robust Optimizationcited by 33
  8. 2018Robust Hypothesis Testing Using Wasserstein Uncertainty Setscited by 28
  9. 2020Adversarial Weighting for Domain Adaptation in Regressioncited by 19
  10. 2016Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensorscited by 18
  11. 2018Wasserstein Distributionally Robust Kalman Filteringcited by 17
  12. 2019Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximationcited by 13
  13. 2013Semi-Supervised Domain Adaptation with Non-Parametric Copulascited by 8
  14. 2019Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimizationcited by 8
  15. 2020Robust Bayesian Classification Using an Optimistic Score Ratiocited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 6; 2023: 1; 2024: 5; 2025: 0; 2026: 1.

14 papers.

Sort:

  1. 2022Counterfactual Plans under Distributional Ambiguitycited by 19
  2. 2021Meta Two-Sample Testing: Learning Kernels for Testing with Limited Datacited by 18
  3. 2022Robust Bayesian Recoursecited by 18
  4. 2023Distributionally Robust Recourse Actioncited by 12
  5. 2022Distributionally Robust Fair Principal Components via Geodesic Descentscited by 9
  6. 2022A Class of Geometric Structures in Transfer Learning: Minimax Bounds and Optimalitycited by 9
  7. 2024A Unified Data Representation Learning for Non-parametric Two-sample Testingcited by 6
  8. 2024Universal generalization guarantees for Wasserstein distributionally robust modelscited by 5
  9. 2024Contextual Optimization under Covariate Shift: A Robust Approach by Intersecting Wasserstein Ballscited by 4
  10. 2022Wasserstein Distributionally Robust Optimization with Wasserstein Barycenterscited by 3
  11. 2022Distributionally Robust Domain Adaptationcited by 2
  12. 2024A Geometric Unification of Distributionally Robust Covariance Estimators: Shrinking the Spectrum by Inflating the Ambiguity Setcited by 2
2 more
  1. 2024Distributionally and Adversarially Robust Logistic Regression via Intersecting Wasserstein Ballscited by 0
  2. 2026Wasserstein Distributionally Robust Risk-Sensitive Estimation via Conditional Value-at-Riskcited by 0