mlsanityData to 7 Oct 2026

Sever: A Robust Meta-Algorithm for Stochastic Optimization

arXiv 1803.02815 ↗First posted 7 Mar 2018cs.LG cs.AI cs.DScited by 123

Not on the map. Why?

Cited by 20 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In high dimensions, most machine learning methods are brittle to even a small fraction of structured outliers. To address this, we introduce a new meta-algorithm that can take in a base learner such as least squares or stochastic gradient descent, and harden the learner to be resistant to outliers. Our method, Sever, possesses strong theoretical guarantees yet is also highly scalable -- beyond running the base learner itself, it only requires computing the top singular vector of a certain n × d matrix. We apply Sever on a drug design dataset and a spam classification dataset, and find that in both cases it has substantially greater robustness than several baselines. On the spam dataset, with 1% corruptions, we achieved 7.4% test error, compared to 13.4%-20.5% for the baselines, and 3% error on the uncorrupted dataset. Similarly, on the drug design dataset, with 10% corruptions, we achieved 1.42 mean-squared error test error, compared to 1.51-2.33 for the baselines, and 1.23 error on the uncorrupted dataset.

Key facts. Cited by 123 papers in the map (data through 7 Oct 2026). First posted on arXiv 7 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 28; 2023: 20; 2024: 19; 2025: 12; 2026: 11.

123 papers.

Sort:

By area:

  1. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  2. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  3. 2022Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoningcited by 93
  4. 2021Robust and Differentially Private Mean Estimationcited by 66
  5. 2022Byzantine Machine Learning Made Easy by Resilient Averaging of Momentumscited by 63
  6. 2021Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Trainingcited by 58
  7. 2021Property Inference From Poisoningcited by 56
  8. 2021Corruption-Robust Offline Reinforcement Learningcited by 51
  9. 2022Improved Certified Defenses against Data Poisoning with (Deterministic) Finite Aggregationcited by 50
  10. 2021On Tilted Losses in Machine Learning: Theory and Applicationscited by 42
  11. 2022Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attackscited by 37
  12. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
38 more
  1. 2021Robust Policy Gradient against Strong Data Corruptioncited by 30
  2. 2022Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guaranteescited by 30
  3. 2021De-Pois: An Attack-Agnostic Defense against Data Poisoning Attackscited by 29
  4. 2021Statistical Query Lower Bounds for List-Decodable Linear Regressioncited by 25
  5. 2022One-shot Neural Backdoor Erasing via Adversarial Weight Maskingcited by 25
  6. 2022Indiscriminate Data Poisoning Attacks on Neural Networkscited by 24
  7. 2022Robust Sparse Mean Estimation via Sum of Squarescited by 23
  8. 2023BayBFed: Bayesian Backdoor Defense for Federated Learningcited by 23
  9. 2023Exploring the Limits of Model-Targeted Indiscriminate Data Poisoning Attackscited by 23
  10. 2021Clustering Mixture Models in Almost-Linear Time via List-Decodable Mean Estimationcited by 21
  11. 2021Efficient Algorithms for Learning from Coarse Labelscited by 21
  12. 2021Certifying Robustness to Programmable Data Bias in Decision Treescited by 21
  13. 2022Streaming Algorithms for High-Dimensional Robust Statisticscited by 21
  14. 2021Defense Against Reward Poisoning Attacks in Reinforcement Learningcited by 20
  15. 2021Robust Training in High Dimensions via Block Coordinate Geometric Median Descentcited by 20
  16. 2021Fairness-Aware PAC Learning from Corrupted Datacited by 18
  17. 2021Robust Federated Learning with Attack-Adaptive Aggregationcited by 17
  18. 2023Run-Off Election: Improved Provable Defense against Data Poisoning Attackscited by 16
  19. 2021Robust Regression Revisited: Acceleration and Improved Estimation Ratescited by 15
  20. 2022Poisoning Attacks and Defenses on Artificial Intelligence: A Surveycited by 15
  21. 2021Outlier-Robust Learning of Ising Models Under Dobrushin's Conditioncited by 14
  22. 2021Outlier-Robust Sparse Estimation via Non-Convex Optimizationcited by 14
  23. 2021Learning and Certification under Instance-targeted Poisoningcited by 13
  24. 2022Byzantine-Robust Online and Offline Distributed Reinforcement Learningcited by 13
  25. 2022Outlier-Robust Sparse Mean Estimation for Heavy-Tailed Distributionscited by 13
  26. 2021Learning GMMs with Nearly Optimal Robustness Guaranteescited by 12
  27. 2022Minimax Rates for Robust Community Detectioncited by 12
  28. 2022Lethal Dose Conjecture on Data Poisoningcited by 12
  29. 2022Estimation Contracts for Outlier-Robust Geometric Perceptioncited by 11
  30. 2023Robust Nonparametric Regression under Poisoning Attackcited by 11
  31. 2021ReLU Regression with Massart Noisecited by 10
  32. 2022Robust Imitation Learning from Corrupted Demonstrationscited by 10
  33. 2023Temporal Robustness against Data Poisoningcited by 10
  34. 2023Nearly-Linear Time and Streaming Algorithms for Outlier-Robust PCAcited by 10
  35. 2024SoS Certifiability of Subgaussian Distributions and its Algorithmic Applicationscited by 10
  36. 2024Game-Theoretic Defenses for Robust Conformal Prediction Against Adversarial Attacks in Medical Imagingcited by 10
  37. 2023Near Optimal Private and Robust Linear Regressioncited by 9
  38. 2021Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameterscited by 8

50 most cited of 123 All 123 (JSON)