mlsanityData to 14 Oct 2026

Best-Effort Adaptation

arXiv 2305.05816 ↗First posted 10 May 2023cs.LG stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

We study a problem of best-effort adaptation motivated by several applications and considerations, which consists of determining an accurate predictor for a target domain, for which a moderate amount of labeled samples are available, while leveraging information from another domain for which substantially more labeled samples are at one's disposal. We present a new and general discrepancy-based theoretical analysis of sample reweighting methods, including bounds holding uniformly over the weights. We show how these bounds can guide the design of learning algorithms that we discuss in detail. We further show that our learning guarantees and algorithms provide improved solutions for standard domain adaptation problems, for which few labeled data or none are available from the target domain. We finally report the results of a series of experiments demonstrating the effectiveness of our best-effort adaptation and domain adaptation algorithms, as well as comparisons with several baselines. We also discuss how our analysis can benefit the design of principled solutions for fine-tuning.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 57 of its 141 references that are in the map. First posted on arXiv 10 May 2023.

Builds on

57 of 141 references.

References · 57

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  5. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,780
  7. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  8. 2021Convex optimizationcited by 2,515
  9. 2018Deep contextualized word representationscited by 2,290
  10. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,331
  11. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,329
  12. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
38 more
  1. 2018On First-Order Meta-Learning Algorithmscited by 1,018
  2. 2018Deep Visual Domain Adaptation: A Surveycited by 635
  3. 2013Domain Generalization via Invariant Feature Representationcited by 623
  4. 2015Optimal Transport for Domain Adaptationcited by 463
  5. 2019Agnostic Federated Learningcited by 456
  6. 2015Return of Frustratingly Easy Domain Adaptationcited by 391
  7. 2016Unsupervised Domain Adaptation with Residual Transfer Networkscited by 341
  8. 2019Semi-supervised Domain Adaptation via Minimax Entropycited by 335
  9. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  10. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  11. 2015Skip-Thought Vectorscited by 322
  12. 2016Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networkscited by 308
  13. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  14. 2020Universal Source-Free Domain Adaptationcited by 220
  15. 2015Simultaneous Deep Transfer Across Domains and Taskscited by 206
  16. 2018Multi-Adversarial Domain Adaptationcited by 196
  17. 2015The Benefit of Multitask Representation Learningcited by 195
  18. 2021Muppet: Massive Multi-task Representations with Pre-Finetuningcited by 192
  19. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 168
  20. 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
  21. 2017Few-Shot Adversarial Domain Adaptationcited by 111
  22. 2016Theoretical Analysis of Domain Adaptation with Optimal Transportcited by 105
  23. 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
  24. 2020Toxicity Detection: Does Context Really Matter?cited by 93
  25. 2018Visual Domain Adaptation with Manifold Embedded Distribution Alignmentcited by 91
  26. 2013A PAC-Bayesian bound for Lifelong Learningcited by 69
  27. 2019Provable Guarantees for Gradient-Based Meta-Learningcited by 67
  28. 2018Marginal Singularity, and the Benefits of Labels in Covariate-Shiftcited by 65
  29. 2020On the Value of Target Data in Transfer Learningcited by 65
  30. 2018Algorithms and Theory for Multiple-Source Adaptationcited by 54
  31. 2018Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learningcited by 52
  32. 2016Learning Attributes Equals Multi-Source Domain Generalizationcited by 44
  33. 2019Few-shot Adaptive Faster R-CNNcited by 42
  34. 2019Domain Aggregation Networks for Multi-Source Domain Adaptationcited by 37
  35. 2017Robust Optimization for Non-Convex Objectivescited by 35
  36. 2019Robust Learning from Untrusted Sourcescited by 27
  37. 2016Hypothesis Transfer Learning via Transformation Functionscited by 26
  38. 2020A One-step Approach to Covariate Shift Adaptationcited by 21

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 5.

7 papers.

  1. 2025Learning Neural Networks with Distribution Shift: Efficiently Certifiable Guaranteescited by 4
  2. 2025Revisiting Frank-Wolfe for Structured Nonconvex Optimizationcited by 2
  3. 2025A Distributionally Robust Framework for Nuisance in Causal Effect Estimationcited by 1
  4. 2025Scalable DC Optimization via Adaptive Frank-Wolfe Algorithmscited by 1
  5. 2023Differentially Private Domain Adaptation with Theoretical Guaranteescited by 0
  6. 2024Enhancing selectivity using Wasserstein distance based reweighingcited by 0
  7. 2025Allocating Variance to Maximize Expectationcited by 0