{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UNQ2VCI25YFQ5K54L67MPJNNDM","short_pith_number":"pith:UNQ2VCI2","schema_version":"1.0","canonical_sha256":"a361aa891aee0b0eabbc5fbec7a5ad1b1e2ae22872b63f66ee8dabbd3f457272","source":{"kind":"arxiv","id":"2410.13749","version":2},"attestation_state":"computed","paper":{"title":"Supervised Kernel Thinning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Albert Gong, Kyuseong Choi, Raaz Dwivedi","submitted_at":"2024-10-17T16:48:51Z","abstract_excerpt":"The kernel thinning algorithm of Dwivedi & Mackey (2024) provides a better-than-i.i.d. compression of a generic set of points. By generating high-fidelity coresets of size significantly smaller than the input points, KT is known to speed up unsupervised tasks like Monte Carlo integration, uncertainty quantification, and non-parametric hypothesis testing, with minimal loss in statistical accuracy. In this work, we generalize the KT algorithm to speed up supervised learning problems involving kernel methods. Specifically, we combine two classical algorithms--Nadaraya-Watson (NW) regression or ke"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.13749","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-17T16:48:51Z","cross_cats_sorted":["math.ST","stat.ML","stat.TH"],"title_canon_sha256":"d86ccf708a4b43ae92b62ee09fc6db49a5bfa96f92aeefea0fc56f908eef6875","abstract_canon_sha256":"64de35d2df25956e22ab1a4bc205a9e2bd550512e8d8bf664109d33f14422f88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:17.067666Z","signature_b64":"9u47z4n5ROObLSEs2MVjZMvOkvQ3VfSAfBhWWioSDPgXwZeqyhlhXTv+Ny5KVsHEY/rQL4zjfRSn3Yi/UZenCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a361aa891aee0b0eabbc5fbec7a5ad1b1e2ae22872b63f66ee8dabbd3f457272","last_reissued_at":"2026-07-05T10:01:17.067089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:17.067089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Supervised Kernel Thinning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Albert Gong, Kyuseong Choi, Raaz Dwivedi","submitted_at":"2024-10-17T16:48:51Z","abstract_excerpt":"The kernel thinning algorithm of Dwivedi & Mackey (2024) provides a better-than-i.i.d. compression of a generic set of points. By generating high-fidelity coresets of size significantly smaller than the input points, KT is known to speed up unsupervised tasks like Monte Carlo integration, uncertainty quantification, and non-parametric hypothesis testing, with minimal loss in statistical accuracy. In this work, we generalize the KT algorithm to speed up supervised learning problems involving kernel methods. Specifically, we combine two classical algorithms--Nadaraya-Watson (NW) regression or ke"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.13749","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.13749/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.13749","created_at":"2026-07-05T10:01:17.067158+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.13749v2","created_at":"2026-07-05T10:01:17.067158+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.13749","created_at":"2026-07-05T10:01:17.067158+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNQ2VCI25YFQ","created_at":"2026-07-05T10:01:17.067158+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNQ2VCI25YFQ5K54","created_at":"2026-07-05T10:01:17.067158+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNQ2VCI2","created_at":"2026-07-05T10:01:17.067158+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.20194","citing_title":"Coreset selection for the Sinkhorn divergence and generic smooth divergences","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM","json":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM.json","graph_json":"https://pith.science/api/pith-number/UNQ2VCI25YFQ5K54L67MPJNNDM/graph.json","events_json":"https://pith.science/api/pith-number/UNQ2VCI25YFQ5K54L67MPJNNDM/events.json","paper":"https://pith.science/paper/UNQ2VCI2"},"agent_actions":{"view_html":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM","download_json":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM.json","view_paper":"https://pith.science/paper/UNQ2VCI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.13749&json=true","fetch_graph":"https://pith.science/api/pith-number/UNQ2VCI25YFQ5K54L67MPJNNDM/graph.json","fetch_events":"https://pith.science/api/pith-number/UNQ2VCI25YFQ5K54L67MPJNNDM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM/action/storage_attestation","attest_author":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM/action/author_attestation","sign_citation":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM/action/citation_signature","submit_replication":"https://pith.science/pith/UNQ2VCI25YFQ5K54L67MPJNNDM/action/replication_record"}},"created_at":"2026-07-05T10:01:17.067158+00:00","updated_at":"2026-07-05T10:01:17.067158+00:00"}