SOTAVerified

Two-sample testing

In statistical hypothesis testing, a two-sample test is a test performed on the data of two random samples, each independently obtained from a different given population. The purpose of the test is to determine whether the difference between these two populations is statistically significant. The statistics used in two-sample tests can be used to solve many machine learning problems, such as domain adaptation, covariate shift and generative adversarial networks.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 11–20 of 338 papers

TitleStatusHype
Machine Learning for Two-Sample Testing under Right-Censored Data: A Simulation StudyCode0
Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier FeaturesCode0
Network two-sample test for block models—0
Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances—0
Collaborative non-parametric two-sample testing—0
Variable Selection in Maximum Mean Discrepancy for Interpretable Distribution Comparison—0
Deep anytime-valid hypothesis testingCode0
A framework for paired-sample hypothesis testing for high-dimensional data—0
On the Exploration of Local Significant Differences For Two-Sample Test—0
Kernel-Based Tests for Likelihood-Free Hypothesis TestingCode0
Show:102550
← PrevPage 2 of 34Next →
All datasetsBlob (9 modes, 40 for each)CIFAR-10 vs CIFAR-10.1 (1000 samples)HDGM (d=10, N=4000)HIGGS Data SetMNIST vs Fake MNIST

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1MMD-DAvg accuracy98.5—Unverified
#ModelMetricClaimedVerifiedStatus
1MMD-DAvg accuracy74.4—Unverified
#ModelMetricClaimedVerifiedStatus
1MMD-DAvg accuracy65.9—Unverified
#ModelMetricClaimedVerifiedStatus
1MMD-DAvg accuracy57.9—Unverified
#ModelMetricClaimedVerifiedStatus
1MMD-DAvg accuracy91—Unverified