mlsanityData to 14 Oct 2026

Kernels, Data & Physics

arXiv 2307.02693 ↗First posted 5 Jul 2023cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Lecture notes from the course given by Professor Julia Kempe at the summer school "Statistical physics of Machine Learning" in Les Houches. The notes discuss the so-called NTK approach to problems in machine learning, which consists of gaining an understanding of generally unsolvable problems by finding a tractable kernel formulation. The notes are mainly focused on practical applications such as data distillation and adversarial robustness, examples of inductive bias are also discussed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 5 Jul 2023.

Builds on

44 of 54 references.

References · 44

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,621
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  8. 2016Adversarial Machine Learning at Scalecited by 936
  9. 2018Robustness May Be at Odds with Accuracycited by 880
  10. 2019Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descentcited by 738
  11. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 573
  12. 2014Breaking the Curse of Dimensionality with Convex Neural Networkscited by 331
32 more
  1. 2018Adversarially Robust Generalization Requires More Datacited by 318
  2. 2021The Intrinsic Dimension of Images and Its Impact on Learningcited by 315
  3. 2018Dataset Distillationcited by 230
  4. 2020Dataset Meta-Learning from Kernel Ridge-Regressioncited by 230
  5. 2021Dataset Distillation with Infinitely Wide Convolutional Networkscited by 218
  6. 2020Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networkscited by 200
  7. 2020Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the Neural Tangent Kernelcited by 187
  8. 2019On the Inductive Bias of Neural Tangent Kernelscited by 177
  9. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  10. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 161
  11. 2018ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detectorcited by 159
  12. 2021A Universal Law of Robustness via Isoperimetrycited by 151
  13. 2020Frequency Bias in Neural Networks for Input of Non-Uniform Densitycited by 140
  14. 2016Toward Deeper Understanding of Neural Networks: The Power of Initialization and a Dual View on Expressivitycited by 138
  15. 2021Learning curves of generic features maps for realistic datasets with a teacher-student modelcited by 126
  16. 2019Harnessing the Power of Infinitely Wide Deep Nets on Small-data Taskscited by 87
  17. 2020Deep Equals Shallow for ReLU Networks in Kernel Regimescited by 85
  18. 2021What can linearized neural networks actually say about generalization?cited by 49
  19. 2018On the Geometry of Adversarial Examplescited by 43
  20. 2021A linearized framework and a new benchmark for model selection for fine-tuningcited by 41
  21. 2020Why Are Convolutional Nets More Sample-Efficient than Fully-Connected Nets?cited by 34
  22. 2021KNAS: Green Neural Architecture Searchcited by 33
  23. 2021Approximation and Learning with Deep Convolutional Models: a Kernel Perspectivecited by 31
  24. 2020Finding trainable sparse networks through Neural Tangent Transfercited by 28
  25. 2021Locality defeats the curse of dimensionality in convolutional teacher-student scenarioscited by 26
  26. 2022What Can the Neural Tangent Kernel Tell Us About Adversarial Robustness?cited by 21
  27. 2020Computational Separation Between Convolutional and Fully-Connected Networkscited by 20
  28. 2022Infinite Recommendation Networks: A Data-Centric Approachcited by 20
  29. 2021Simple, Fast, and Flexible Framework for Matrix Completion with Infinite Width Neural Networkscited by 17
  30. 2021Eigenspace Restructuring: a Principle of Space and Frequency in Neural Networkscited by 17
  31. 2022Can we achieve robustness from data alone?cited by 16
  32. 2022Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional datacited by 12

Built on by

Not cited yet.