{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-kernel-tests-without-data-splitting","title":"Learning Kernel Tests Without Data Splitting","arxiv_id":"2006.02286","date":"2020-06-03","proceeding":"NeurIPS 2020 12","authors":["Jonas M. Kübler","Wittawat Jitkrittum","Bernhard Schölkopf","Krikamol Muandet"],"abstract":"Modern large-scale kernel-based tests such as maximum mean discrepancy (MMD) and kernelized Stein discrepancy (KSD) optimize kernel hyperparameters on a held-out sample via data splitting to obtain the most powerful test statistics. While data splitting results in a tractable null distribution, it suffers from a reduction in test power due to smaller test sample size. Inspired by the selective inference framework, we propose an approach that enables learning the hyperparameters and testing on the full sample without data splitting. Our approach can correctly calibrate the test in the presence of such dependency, and yield a test threshold in closed form. At the same significance level, our approach's test power is empirically larger than that of the data-splitting approach, regardless of its split proportion.","url_abs":"https://arxiv.org/abs/2006.02286v3","url_pdf":"https://arxiv.org/pdf/2006.02286v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-kernel-tests-without-data-splitting","repo_url":"https://github.com/MPI-IS/tests-wo-splitting","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.02286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.02286"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/jmkuebler/tests-wo-splitting","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MPI-IS/tests-wo-splitting","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9583f41dee5cf9d4","entry":"blobs","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/datasets/generate_data.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/datasets/generate_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9583f41dee5cf9d4"}},{"code_sha256_prefix":"5d33a90d85794f63","entry":"generate_samples","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/datasets/generate_data.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/datasets/generate_data.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d33a90d85794f63"}},{"code_sha256_prefix":"12f03b12b67e85ec","entry":"median","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/median.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/median.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"12f03b12b67e85ec"}},{"code_sha256_prefix":"f1baa9637253a70c","entry":"preprocessing","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/wald.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/wald.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1baa9637253a70c"}},{"code_sha256_prefix":"5e845c7b9aa0179c","entry":"pvalue","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/pvalue.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/pvalue.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5e845c7b9aa0179c"}},{"code_sha256_prefix":"cba0bc0d26e5f751","entry":"split_test","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/split.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/split.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cba0bc0d26e5f751"}},{"code_sha256_prefix":"d2aae90c4e1db51c","entry":"truncated_gaussian","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/ost.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/ost.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d2aae90c4e1db51c"}},{"code_sha256_prefix":"b8733b899ab4f726","entry":"truncation","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/ost.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/ost.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b8733b899ab4f726"}},{"code_sha256_prefix":"04061bc1a18c05d2","entry":"wald_test","repo":"MPI-IS/tests-wo-splitting","repo_kind":"official","path":"tests_wo_split/methods/wald.py","file_url":"https://github.com/MPI-IS/tests-wo-splitting/blob/HEAD/tests_wo_split/methods/wald.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04061bc1a18c05d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}