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 1–50 of 338 papers

TitleStatusHype
Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference SettingCode1
Model Equality Testing: Which Model Is This API Serving?Code1
Addressing Maximization Bias in Reinforcement Learning with Two-Sample TestingCode1
Learning Deep Kernels for Non-Parametric Two-Sample TestsCode1
AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularityCode1
Testing Goodness of Fit of Conditional Density Models with KernelsCode1
Towards Probabilistic Verification of Machine UnlearningCode1
Expert-Supervised Reinforcement Learning for Offline Policy Learning and EvaluationCode1
Safe TestingCode1
Learning Opinion Dynamics From Social TracesCode1
MMD Aggregated Two-Sample TestCode1
Statistical comparison of classifiers through Bayesian hierarchical modellingCode1
Decision-Making with Auto-Encoding Variational BayesCode1
AutoML Two-Sample TestCode1
Machine Learning for Two-Sample Testing under Right-Censored Data: A Simulation StudyCode0
A Witness Two-Sample TestCode0
Measuring Gender Bias in Word Embeddings across Domains and Discovering New Gender Bias Word CategoriesCode0
Kernel-Based Tests for Likelihood-Free Hypothesis TestingCode0
Interpreting Black Box Models via Hypothesis TestingCode0
Kernel Conditional Moment Test via Maximum Moment RestrictionCode0
Meta Two-Sample Testing: Learning Kernels for Testing with Limited DataCode0
Efficient Nonparametric Smoothness EstimationCode0
Generative Moment Matching NetworksCode0
Interpretability of Multivariate Brain Maps in Brain Decoding: Definition and QuantificationCode0
Adversarial Sample Detection for Deep Neural Network through Model Mutation TestingCode0
Intrinsic Sliced Wasserstein Distances for Comparing Collections of Probability Distributions on Manifolds and GraphsCode0
A U-statistic Approach to Hypothesis Testing for Structure Discovery in Undirected Graphical ModelsCode0
A label-efficient two-sample testCode0
A Permutation-free Kernel Two-Sample TestCode0
Deep anytime-valid hypothesis testingCode0
Data-adaptive statistics for multiple hypothesis testing in high-dimensional settingsCode0
A Meta-Analysis of the Anomaly Detection ProblemCode0
Copy Move Source-Target Disambiguation through Multi-Branch CNNsCode0
Failing Loudly: An Empirical Study of Methods for Detecting Dataset ShiftCode0
Compress Then Test: Powerful Kernel Testing in Near-linear TimeCode0
A Differentially Private Kernel Two-Sample TestCode0
Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier FeaturesCode0
Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithmCode0
Comparing distributions: _1 geometry improves kernel two-sample testingCode0
Event Outlier Detection in Continuous TimeCode0
A Test for Shared Patterns in Cross-modal Brain Activation AnalysisCode0
Credal Two-Sample Tests of Epistemic UncertaintyCode0
Conditional Independence Testing using Generative Adversarial NetworksCode0
B-tests: Low Variance Kernel Two-Sample TestsCode0
Diagonal Discriminant Analysis with Feature Selection for High Dimensional DataCode0
Detecting Rewards Deterioration in Episodic Reinforcement LearningCode0
Gaussian Differential PrivacyCode0
General Frameworks for Conditional Two-Sample TestingCode0
Graphon based Clustering and Testing of Networks: Algorithms and TheoryCode0
The hypergeometric test performs comparably to TF-IDF on standard text analysis tasksCode0
Show:102550
← PrevPage 1 of 7Next →
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