Learning deep kernels for non-parametric two-sample tests
We propose a class of kernel-based two-sample tests, which aim to determine whether two
sets of samples are drawn from the same distribution. Our tests are constructed from kernels …
sets of samples are drawn from the same distribution. Our tests are constructed from kernels …
Convergence of flow-based generative models via proximal gradient descent in Wasserstein space
Flow-based generative models enjoy certain advantages in computing the data generation
and the likelihood, and have recently shown competitive empirical performance. Compared …
and the likelihood, and have recently shown competitive empirical performance. Compared …
Sequential predictive two-sample and independence testing
A Podkopaev, A Ramdas - Advances in neural information …, 2023 - proceedings.neurips.cc
We study the problems of sequential nonparametric two-sample and independence testing.
Sequential tests process data online and allow using observed data to decide whether to …
Sequential tests process data online and allow using observed data to decide whether to …
Neural tangent kernel maximum mean discrepancy
We present a novel neural network Maximum Mean Discrepancy (MMD) statistic by
identifying a new connection between neural tangent kernel (NTK) and MMD. This …
identifying a new connection between neural tangent kernel (NTK) and MMD. This …
A deep network construction that adapts to intrinsic dimensionality beyond the domain
A Cloninger, T Klock - Neural Networks, 2021 - Elsevier
We study the approximation of two-layer compositions f (x)= g (ϕ (x)) via deep networks with
ReLU activation, where ϕ is a geometrically intuitive, dimensionality reducing feature map …
ReLU activation, where ϕ is a geometrically intuitive, dimensionality reducing feature map …
[PDF][PDF] Comparing distributions by measuring differences that affect decision making
Measuring the discrepancy between two probability distributions is a fundamental problem
in machine learning and statistics. We propose a new class of discrepancies based on the …
in machine learning and statistics. We propose a new class of discrepancies based on the …
AutoML two-sample test
Two-sample tests are important in statistics and machine learning, both as tools for scientific
discovery as well as to detect distribution shifts. This led to the development of many …
discovery as well as to detect distribution shifts. This led to the development of many …
R-divergence for estimating model-oriented distribution discrepancy
Real-life data are often non-IID due to complex distributions and interactions, and the
sensitivity to the distribution of samples can differ among learning models. Accordingly, a …
sensitivity to the distribution of samples can differ among learning models. Accordingly, a …
Convergence of flow-based generative models via proximal gradient descent in wasserstein space
Flow-based generative models enjoy certain advantages in computing the data generation
and the likelihood, and have recently shown competitive empirical performance. Compared …
and the likelihood, and have recently shown competitive empirical performance. Compared …
E-valuating classifier two-sample tests
We propose E-C2ST, a classifier two-sample test for high-dimensional data based on E-
values. Compared to $ p $-values-based tests, tests with E-values have finite sample …
values. Compared to $ p $-values-based tests, tests with E-values have finite sample …