{"url":"/task/hypothesis-testing","name":"Two-sample testing","slug":"hypothesis-testing","description_markdown":"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.","categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":338,"papers_with_code":84,"benchmarks":5,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/two-sample-testing-on-blob-9-modes-40-for","slug":"two-sample-testing-on-blob-9-modes-40-for","dataset":"Blob (9 modes, 40 for each)","dataset_url":null,"rows_in_archive":1,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"MMD-D","paper_title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","paper_url":"/paper/learning-deep-kernels-for-non-parametric-two","paper_date":"2020-02-21","arxiv_id":"2002.09116","code_links":[{"title":"fengliu90/DK-for-TST","url":"https://github.com/fengliu90/DK-for-TST"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/two-sample-testing-on-cifar-10-vs-cifar-10-1-1","slug":"two-sample-testing-on-cifar-10-vs-cifar-10-1-1","dataset":"CIFAR-10 vs CIFAR-10.1 (1000 samples)","dataset_url":null,"rows_in_archive":1,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"MMD-D","paper_title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","paper_url":"/paper/learning-deep-kernels-for-non-parametric-two","paper_date":"2020-02-21","arxiv_id":"2002.09116","code_links":[{"title":"fengliu90/DK-for-TST","url":"https://github.com/fengliu90/DK-for-TST"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/two-sample-testing-on-hdgm-d-10-n-4000","slug":"two-sample-testing-on-hdgm-d-10-n-4000","dataset":"HDGM (d=10, N=4000)","dataset_url":null,"rows_in_archive":1,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"MMD-D","paper_title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","paper_url":"/paper/learning-deep-kernels-for-non-parametric-two","paper_date":"2020-02-21","arxiv_id":"2002.09116","code_links":[{"title":"fengliu90/DK-for-TST","url":"https://github.com/fengliu90/DK-for-TST"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/two-sample-testing-on-higgs-data-set","slug":"two-sample-testing-on-higgs-data-set","dataset":"HIGGS Data Set","dataset_url":"/dataset/higgs-data-set","rows_in_archive":1,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"MMD-D","paper_title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","paper_url":"/paper/learning-deep-kernels-for-non-parametric-two","paper_date":"2020-02-21","arxiv_id":"2002.09116","code_links":[{"title":"fengliu90/DK-for-TST","url":"https://github.com/fengliu90/DK-for-TST"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/two-sample-testing-on-mnist-vs-fake-mnist","slug":"two-sample-testing-on-mnist-vs-fake-mnist","dataset":"MNIST vs Fake MNIST","dataset_url":null,"rows_in_archive":1,"metrics":["Avg accuracy"],"first_row_in_archive_order":{"model":"MMD-D","paper_title":"Learning Deep Kernels for Non-Parametric Two-Sample Tests","paper_url":"/paper/learning-deep-kernels-for-non-parametric-two","paper_date":"2020-02-21","arxiv_id":"2002.09116","code_links":[{"title":"fengliu90/DK-for-TST","url":"https://github.com/fengliu90/DK-for-TST"}],"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/higgs-data-set","name":"HIGGS Data Set","full_name":"","num_papers_in_archive":14}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":84,"tagged_in_all":338,"items":[{"url":"/paper/pacgan-the-power-of-two-samples-in-generative","title":"PacGAN: The power of two samples in generative adversarial networks","date":"2017-12-12","arxiv_id":"1712.04086","repositories_listed":7,"syntology":null},{"url":"/paper/adversarial-sample-detection-for-deep-neural","title":"Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing","date":"2018-12-14","arxiv_id":"1812.05793","repositories_listed":5,"syntology":null},{"url":"/paper/mgcpy-a-comprehensive-high-dimensional","title":"hyppo: A Multivariate Hypothesis Testing Python Package","date":"2019-07-03","arxiv_id":"1907.02088","repositories_listed":4,"syntology":null},{"url":"/paper/association-of-genomic-subtypes-of-lower","title":"Association of genomic subtypes of lower-grade gliomas with shape features automatically extracted by a deep learning algorithm","date":"2019-06-09","arxiv_id":"1906.03720","repositories_listed":4,"syntology":null},{"url":"/paper/automl-two-sample-test","title":"AutoML Two-Sample Test","date":"2022-06-17","arxiv_id":"2206.08843","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/mmd-aggregated-two-sample-test","title":"MMD Aggregated Two-Sample Test","date":"2021-10-28","arxiv_id":"2110.15073","repositories_listed":3,"syntology":{"n":15,"n_ran":4,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/gaussian-differential-privacy","title":"Gaussian Differential Privacy","date":"2019-05-07","arxiv_id":"1905.02383","repositories_listed":3,"syntology":null},{"url":"/paper/generative-moment-matching-networks","title":"Generative Moment Matching Networks","date":"2015-02-10","arxiv_id":"1502.02761","repositories_listed":3,"syntology":null},{"url":"/paper/quantifying-statistical-significance-of-1","title":"Quantifying Statistical Significance of Neural Network-based Image Segmentation by Selective Inference","date":"2020-10-05","arxiv_id":"2010.01823","repositories_listed":2,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":8}},{"url":"/paper/expert-supervised-reinforcement-learning-for","title":"Expert-Supervised Reinforcement Learning for Offline Policy Learning and Evaluation","date":"2020-06-23","arxiv_id":"2006.13189","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":11}},{"url":"/paper/ai-feynman-2-0-pareto-optimal-symbolic","title":"AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity","date":"2020-06-18","arxiv_id":"2006.10782","repositories_listed":2,"syntology":{"n":20,"n_ran":5,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/confidence-sets-and-hypothesis-testing-in-a","title":"Confidence Sets and Hypothesis Testing in a Likelihood-Free Inference Setting","date":"2020-02-24","arxiv_id":"2002.10399","repositories_listed":2,"syntology":null},{"url":"/paper/decision-making-with-auto-encoding","title":"Decision-Making with Auto-Encoding Variational Bayes","date":"2020-02-17","arxiv_id":"2002.07217","repositories_listed":2,"syntology":null},{"url":"/paper/comparing-distributions-ell_1-geometry","title":"Comparing distributions: $\\ell_1$ geometry improves kernel two-sample testing","date":"2019-09-19","arxiv_id":"1909.09264","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/scalable-and-efficient-hypothesis-testing","title":"Scalable and Efficient Hypothesis Testing with Random Forests","date":"2019-04-16","arxiv_id":"1904.07830","repositories_listed":2,"syntology":null},{"url":"/paper/failing-loudly-an-empirical-study-of-methods","title":"Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift","date":"2018-10-29","arxiv_id":"1810.11953","repositories_listed":2,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/a-differentially-private-kernel-two-sample","title":"A Differentially Private Kernel Two-Sample Test","date":"2018-08-01","arxiv_id":"1808.00380","repositories_listed":2,"syntology":null},{"url":"/paper/statistical-anomaly-detection-via-composite","title":"Statistical Anomaly Detection via Composite Hypothesis Testing for Markov Models","date":"2017-02-27","arxiv_id":"1702.08435","repositories_listed":2,"syntology":null},{"url":"/paper/online-robust-principal-component-analysis","title":"Online Robust Principal Component Analysis with Change Point Detection","date":"2017-02-19","arxiv_id":"1702.05698","repositories_listed":2,"syntology":null},{"url":"/paper/minimax-optimal-two-sample-testing-under","title":"Minimax Optimal Two-Sample Testing under Local Differential Privacy","date":"2024-11-13","arxiv_id":"2411.09064","repositories_listed":1,"syntology":null},{"url":"/paper/model-equality-testing-which-model-is-this","title":"Model Equality Testing: Which Model Is This API Serving?","date":"2024-10-26","arxiv_id":"2410.20247","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":5}},{"url":"/paper/general-frameworks-for-conditional-two-sample","title":"General Frameworks for Conditional Two-Sample Testing","date":"2024-10-22","arxiv_id":"2410.16636","repositories_listed":1,"syntology":null},{"url":"/paper/credal-two-sample-tests-of-epistemic","title":"Credal Two-Sample Tests of Epistemic Uncertainty","date":"2024-10-16","arxiv_id":"2410.12921","repositories_listed":1,"syntology":{"n":12,"n_ran":12,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/machine-learning-for-two-sample-testing-under","title":"Machine Learning for Two-Sample Testing under Right-Censored Data: A Simulation Study","date":"2024-09-12","arxiv_id":"2409.08201","repositories_listed":1,"syntology":null},{"url":"/paper/computational-statistical-trade-off-in-kernel","title":"Computational-Statistical Trade-off in Kernel Two-Sample Testing with Random Fourier Features","date":"2024-07-12","arxiv_id":"2407.08976","repositories_listed":1,"syntology":null},{"url":"/paper/deep-anytime-valid-hypothesis-testing","title":"Deep anytime-valid hypothesis testing","date":"2023-10-30","arxiv_id":"2310.19384","repositories_listed":1,"syntology":null},{"url":"/paper/kernel-based-tests-for-likelihood-free","title":"Kernel-Based Tests for Likelihood-Free Hypothesis Testing","date":"2023-08-17","arxiv_id":"2308.09043","repositories_listed":1,"syntology":null},{"url":"/paper/mmd-fuse-learning-and-combining-kernels-for","title":"MMD-FUSE: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting","date":"2023-06-14","arxiv_id":"2306.08777","repositories_listed":1,"syntology":{"n":15,"n_ran":2,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/the-representation-jensen-shannon-divergence","title":"The Representation Jensen-Shannon Divergence","date":"2023-05-25","arxiv_id":"2305.16446","repositories_listed":1,"syntology":null},{"url":"/paper/multimodal-multi-user-surface-recognition","title":"Multimodal Multi-User Surface Recognition with the Kernel Two-Sample Test","date":"2023-03-08","arxiv_id":"2303.04930","repositories_listed":1,"syntology":null}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}