Neural Tangent Kernel Maximum Mean Discrepancy

06/06/2021
by   Xiuyuan Cheng, et al.
0

We present a novel neural network Maximum Mean Discrepancy (MMD) statistic by identifying a connection between neural tangent kernel (NTK) and MMD statistic. This connection enables us to develop a computationally efficient and memory-efficient approach to compute the MMD statistic and perform neural network 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 assimilate new samples. Theoretically, such a connection allows us to understand the properties of the new test statistic, such as Type-I error and testing power for performing the two-sample test, by leveraging analysis tools for kernel MMD. Numerical experiments on synthetic and real-world datasets validate the theory and demonstrate the effectiveness of the proposed NTK-MMD statistic.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/08/2013

B-tests: Low Variance Kernel Two-Sample Tests

A family of maximum mean discrepancy (MMD) kernel two-sample tests is in...
research
09/25/2019

Classification Logit Two-sample Testing by Neural Networks

The recent success of generative adversarial networks and variational le...
research
05/25/2023

Detecting Adversarial Data by Probing Multiple Perturbations Using Expected Perturbation Score

Adversarial detection aims to determine whether a given sample is an adv...
research
01/10/2019

Closed-form Expressions for Maximum Mean Discrepancy with Applications to Wasserstein Auto-Encoders

The Maximum Mean Discrepancy (MMD) has found numerous applications in st...
research
05/14/2015

Training generative neural networks via Maximum Mean Discrepancy optimization

We consider training a deep neural network to generate samples from an u...
research
09/14/2017

Two-sample Statistics Based on Anisotropic Kernels

The paper introduces a new kernel-based Maximum Mean Discrepancy (MMD) s...
research
06/17/2022

AutoML Two-Sample Test

Two-sample tests are important in statistics and machine learning, both ...

Please sign up or login with your details

Forgot password? Click here to reset