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 1–25 of 338 papers

TitleStatusHype
Model Equality Testing: Which Model Is This API Serving?Code1
AutoML Two-Sample TestCode1
Addressing Maximization Bias in Reinforcement Learning with Two-Sample TestingCode1
MMD Aggregated Two-Sample TestCode1
Expert-Supervised Reinforcement Learning for Offline Policy Learning and EvaluationCode1
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularityCode1
Learning Opinion Dynamics From Social TracesCode1
Towards Probabilistic Verification of Machine UnlearningCode1
Testing Goodness of Fit of Conditional Density Models with KernelsCode1
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference SettingCode1
Learning Deep Kernels for Non-Parametric Two-Sample TestsCode1
Decision-Making with Auto-Encoding Variational BayesCode1
Safe TestingCode1
Statistical comparison of classifiers through Bayesian hierarchical modellingCode1
Leveraging Optimal Transport for Distributed Two-Sample Testing: An Integrated Transportation Distance-based Framework—0
Signature Maximum Mean Discrepancy Two-Sample Statistical Tests—0
From Two Sample Testing to Singular Gaussian Discrimination—0
Advanced Tutorial: Label-Efficient Two-Sample Tests—0
Optimal Algorithms for Augmented Testing of Discrete Distributions—0
A Unified Data Representation Learning for Non-parametric Two-sample Testing—0
Minimax Optimal Two-Sample Testing under Local Differential PrivacyCode0
General Frameworks for Conditional Two-Sample TestingCode0
Credal Two-Sample Tests of Epistemic UncertaintyCode0
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
Show:102550
← PrevPage 1 of 14Next →
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