mlsanityData to 7 Oct 2026

Adversarially Robust Kernel Smoothing

arXiv 2102.08474 ↗First posted 16 Feb 2021cs.LG math.OC stat.MLcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a scalable robust learning algorithm combining kernel smoothing and robust optimization. Our method is motivated by the convex analysis perspective of distributionally robust optimization based on probability metrics, such as the Wasserstein distance and the maximum mean discrepancy. We adapt the integral operator using supremal convolution in convex analysis to form a novel function majorant used for enforcing robustness. Our method is simple in form and applies to general loss functions and machine learning models. Exploiting a connection with optimal transport, we prove theoretical guarantees for certified robustness under distribution shift. Furthermore, we report experiments with general machine learning models, such as deep neural networks, to demonstrate competitive performance with the state-of-the-art certifiable robust learning algorithms based on the Wasserstein distance.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 91 references that are in the map. First posted on arXiv 16 Feb 2021.

Builds on

34 of 91 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  8. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  9. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  10. 2016CVXPY: A Python-Embedded Modeling Language for Convex Optimizationcited by 633
  11. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  12. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 413
22 more
  1. 2019The generalization error of random features regression: Precise asymptotics and double descent curvecited by 410
  2. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  3. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
  4. 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
  5. 2018Just Interpolate: Kernel "Ridgeless" Regression Can Generalizecited by 190
  6. 2016Distributionally Robust Stochastic Optimization with Wasserstein Distancecited by 182
  7. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 182
  8. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  9. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
  10. 2016Variance-based regularization with convex objectivescited by 153
  11. 2015Distributionally Robust Logistic Regressioncited by 124
  12. 2017Regularization via Mass Transportationcited by 79
  13. 2019Metric Learning for Adversarial Robustnesscited by 77
  14. 2019Distributionally Robust Optimization and Generalization in Kernel Methodscited by 73
  15. 2020Kernel regression in high dimensions: Refined analysis beyond double descentcited by 39
  16. 2018Approximation beats concentration? An approximation view on inference with smooth radial kernelscited by 33
  17. 2018Optimal Transport Based Distributionally Robust Optimization: Structural Properties and Iterative Schemescited by 30
  18. 2018On gradient regularizers for MMD GANscited by 28
  19. 2019On the Convergence Proof of AMSGrad and a New Versioncited by 21
  20. 2013Likelihood Robust Optimization for Data-driven Problemscited by 13
  21. 2020Wasserstein Exponential Kernelscited by 10
  22. 2020Kernel Distributionally Robust Optimizationcited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2022Probable Domain Generalization via Quantile Risk Minimizationcited by 66
  2. 2023Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Modelscited by 9
  3. 2023Poison is Not Traceless: Fully-Agnostic Detection of Poisoning Attackscited by 0
  4. 2024A practical approach to evaluating the adversarial distance for machine learning classifierscited by 0