mlsanityData to 7 Oct 2026

Reliable learning in challenging environments

arXiv 2304.03370 ↗First posted 6 Apr 2023cs.LG cs.CRcited by 9

Not on the map. Why?

Abstract (arXiv)

The problem of designing learners that provide guarantees that their predictions are provably correct is of increasing importance in machine learning. However, learning theoretic guarantees have only been considered in very specific settings. In this work, we consider the design and analysis of reliable learners in challenging test-time environments as encountered in modern machine learning problems: namely `adversarial' test-time attacks (in several variations) and `natural' distribution shifts. In this work, we provide a reliable learner with provably optimal guarantees in such settings. We discuss practical implementations of the learner and further show that our algorithm achieves strong positive performance guarantees on several natural examples: for example, linear separators under log-concave distributions or smooth boundary classifiers under smooth probability distributions.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 53 of its 94 references that are in the map. First posted on arXiv 6 Apr 2023.

Builds on

53 of 94 references.

References · 53

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2017On Calibration of Modern Neural Networkscited by 4,860
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  6. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Invariant Risk Minimizationcited by 1,832
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  10. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  11. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  12. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
38 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  2. 2018Robustness May Be at Odds with Accuracycited by 873
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2019Adversarial Training for Free!cited by 638
  5. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  6. 2020Overfitting in adversarially robust deep learningcited by 504
  7. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  8. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  9. 2018Detecting and Correcting for Label Shift with Black Box Predictorscited by 364
  10. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  11. 2019Bridging Theory and Algorithm for Domain Adaptationcited by 332
  12. 2018Adversarially Robust Generalization Requires More Datacited by 318
  13. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  14. 2017Certified Defenses for Data Poisoning Attackscited by 288
  15. 2020The Risks of Invariant Risk Minimizationcited by 262
  16. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  17. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  18. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 148
  19. 2019VC Classes are Adversarially Robustly Learnable, but Only Improperlycited by 83
  20. 2020Precise Tradeoffs in Adversarial Training for Linear Regressioncited by 76
  21. 2019Adversarially robust transfer learningcited by 66
  22. 2020On the Value of Target Data in Transfer Learningcited by 62
  23. 2019Distribution-Independent PAC Learning of Halfspaces with Massart Noisecited by 54
  24. 2015Complexity Theoretic Limitations on Learning Halfspacescited by 50
  25. 2022Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregationcited by 50
  26. 2020Beyond Perturbations: Learning Guarantees with Arbitrary Adversarial Test Examplescited by 44
  27. 2015Efficient Learning of Linear Separators under Bounded Noisecited by 36
  28. 2019Defending against Whitebox Adversarial Attacks via Randomized Discretizationcited by 29
  29. 2017Online Learning with Abstentioncited by 28
  30. 2020Reducing Adversarially Robust Learning to Non-Robust PAC Learningcited by 28
  31. 2021Adversarially Robust Learning with Unknown Perturbation Setscited by 24
  32. 2019On the Hardness of Robust Classificationcited by 23
  33. 2021Exponential Savings in Agnostic Active Learning through Abstentioncited by 23
  34. 2022Robustly-reliable learners under poisoning attackscited by 19
  35. 2020Noise-tolerant, Reliable Active Classification with Comparison Queriescited by 17
  36. 2022Adversarially Robust Learning: A Generic Minimax Optimal Learner and Characterizationcited by 17
  37. 2016Active Learning from Imperfect Labelerscited by 13
  38. 2020On Localized Discrepancy for Domain Adaptationcited by 13

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 6; 2026: 1.

9 papers.

  1. 2024On the Computability of Robust PAC Learningcited by 6
  2. 2025PAC Learning with Improvementscited by 6
  3. 2025On Learning Verifiers and Implications to Chain-of-Thought Reasoningcited by 6
  4. 2026Learning with Monotone Adversarial Corruptionscited by 4
  5. 2024Regularized Robustly Reliable Learners and Instance Targeted Attackscited by 3
  6. 2025Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomnesscited by 2
  7. 2025Conservative classifiers do consistently well with improving agents: characterizing statistical and online learningcited by 2
  8. 2025On the Existence of Consistent Adversarial Attacks in High-Dimensional Linear Classificationcited by 1
  9. 2025Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillationcited by 0