mlsanityData to 7 Oct 2026

Neural Tangent Kernel Maximum Mean Discrepancy

arXiv 2106.03227 ↗First posted 6 Jun 2021stat.ML cs.LG math.STcited by 15

Not on the map. Why?

Abstract (arXiv)

We present a novel neural network Maximum Mean Discrepancy (MMD) statistic by identifying a new connection between neural tangent kernel (NTK) and MMD. This connection enables us to develop a computationally efficient and memory-efficient approach to compute the MMD statistic and perform NTK based two-sample tests towards addressing the long-standing challenge of memory and computational complexity of the MMD statistic, which is essential for online implementation to assimilating new samples. Theoretically, such a connection allows us to understand the NTK test statistic properties, such as the Type-I error and testing power for performing the two-sample test, by adapting existing theories for kernel MMD. Numerical experiments on synthetic and real-world datasets validate the theory and demonstrate the effectiveness of the proposed NTK-MMD statistic.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 30 of its 47 references that are in the map. First posted on arXiv 6 Jun 2021.

Builds on

30 of 47 references.

References · 30

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  2. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  3. 2018On Lazy Training in Differentiable Programmingcited by 671
  4. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 655
  5. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  6. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  7. 2019Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networkscited by 562
  8. 2018Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Datacited by 260
  9. 2016Revisiting Classifier Two-Sample Testscited by 258
  10. 2015Generative Moment Matching Networkscited by 252
  11. 2017MMD GAN: Towards Deeper Understanding of Moment Matching Networkcited by 251
  12. 2019On the Inductive Bias of Neural Tangent Kernelscited by 177
18 more
  1. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
  2. 2020When Do Neural Networks Outperform Kernel Methods?cited by 150
  3. 2018Stochastic Gradient Descent Optimizes Over-parameterized Deep ReLU Networkscited by 139
  4. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 129
  5. 2019Maximum Mean Discrepancy Gradient Flowcited by 123
  6. 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 99
  7. 2019Limitations of Lazy Training of Two-layers Neural Networkscited by 87
  8. 2019Enhanced Convolutional Neural Tangent Kernelscited by 76
  9. 2020On the Similarity between the Laplace and Neural Tangent Kernelscited by 76
  10. 2020Deep Neural Tangent Kernel and Laplace Kernel Have the Same RKHScited by 74
  11. 2021Classifying high-dimensional Gaussian mixtures: Where kernel methods fail and neural networks succeedcited by 67
  12. 2016Interpretable Distribution Features with Maximum Testing Powercited by 63
  13. 2020Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? -- A Neural Tangent Kernel Perspectivecited by 60
  14. 2015Fast Two-Sample Testing with Analytic Representations of Probability Measurescited by 53
  15. 2019Classification Logit Two-sample Testing by Neural Networkscited by 25
  16. 2020Learning Kernel Tests Without Data Splittingcited by 19
  17. 2020Kernel-Based Smoothness Analysis of Residual Networkscited by 19
  18. 2017Two-sample Statistics Based on Anisotropic Kernelscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 2; 2024: 4; 2025: 0; 2026: 2.

15 papers.

Sort:

  1. 2021A Neural Tangent Kernel Perspective of GANscited by 21
  2. 2021Meta Two-Sample Testing: Learning Kernels for Testing with Limited Datacited by 18
  3. 2023Differentially Private Neural Tangent Kernels for Privacy-Preserving Data Generationcited by 15
  4. 2024A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Sciencecited by 14
  5. 2022Nonparametric and Online Change Detection in Multivariate Datastreams using QuantTreecited by 6
  6. 2022A Manifold Two-Sample Test Study: Integral Probability Metric with Neural Networkscited by 5
  7. 2024A Unified Data Representation Learning for Non-parametric Two-sample Testingcited by 5
  8. 2022Neural network-based CUSUM for online change-point detectioncited by 4
  9. 2023Pseudo-keypoint RKHS Learning for Self-supervised 6DoF Pose Estimationcited by 4
  10. 2024Non-Convex Robust Hypothesis Testing using Sinkhorn Uncertainty Setscited by 4
  11. 2026Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Diseasecited by 4
  12. 2021A Deterministic Sampling Method via Maximum Mean Discrepancy Flow with Adaptive Kernelcited by 3
3 more
  1. 2022Neural Stein critics with staged L2-regularizationcited by 2
  2. 2024RIO-CPD: A Riemannian Geometric Method for Correlation-aware Online Change Point Detectioncited by 0
  3. 2026Deep kernel video approximation for unsupervised action segmentationcited by 0