{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UN5WEDFOD56VOITUN26YTOIHGS","short_pith_number":"pith:UN5WEDFO","schema_version":"1.0","canonical_sha256":"a37b620cae1f7d5722746ebd89b90734a538c3388779628a0570e111e84a8de5","source":{"kind":"arxiv","id":"2405.15441","version":4},"attestation_state":"computed","paper":{"title":"Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jie Wang, March Boedihardjo, Yao Xie","submitted_at":"2024-05-24T11:14:56Z","abstract_excerpt":"Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality. Hence, dimensionality reduction is desirable when applied to high-dimensional data with low-dimensional structures. The kernel max-sliced (KMS) Wasserstein distance is developed for this purpose by finding an optimal nonlinear mapping that reduces data into $1$ dimension before computing the Wasserstein distance. However, its theoretical properties have not yet been fully developed. In this paper, we provide sharp finite-sample guarantees under milder "},"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":"2405.15441","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-05-24T11:14:56Z","cross_cats_sorted":["cs.CC","cs.LG"],"title_canon_sha256":"5ccde68c692d1d04e27ae77f232950a2f37954ccf3be19e3d462c578bd9d2ec7","abstract_canon_sha256":"cf18e1dbad498d35d423a67f3670a371f34b3c566f148fbcd57f007e478ec95b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:03.140794Z","signature_b64":"ElUuUhX9gxZM0tioE+8gc8thHCe4OeE8LXLSOJ/IJK82TmZE6R52UxJ33MGGfdtBvtHGQGG93biSo6uFTr48Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a37b620cae1f7d5722746ebd89b90734a538c3388779628a0570e111e84a8de5","last_reissued_at":"2026-07-05T11:39:03.140242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:03.140242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.LG"],"primary_cat":"stat.ML","authors_text":"Jie Wang, March Boedihardjo, Yao Xie","submitted_at":"2024-05-24T11:14:56Z","abstract_excerpt":"Optimal transport has been very successful for various machine learning tasks; however, it is known to suffer from the curse of dimensionality. Hence, dimensionality reduction is desirable when applied to high-dimensional data with low-dimensional structures. The kernel max-sliced (KMS) Wasserstein distance is developed for this purpose by finding an optimal nonlinear mapping that reduces data into $1$ dimension before computing the Wasserstein distance. However, its theoretical properties have not yet been fully developed. In this paper, we provide sharp finite-sample guarantees under milder "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15441","kind":"arxiv","version":4},"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/2405.15441/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":"2405.15441","created_at":"2026-07-05T11:39:03.140296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15441v4","created_at":"2026-07-05T11:39:03.140296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15441","created_at":"2026-07-05T11:39:03.140296+00:00"},{"alias_kind":"pith_short_12","alias_value":"UN5WEDFOD56V","created_at":"2026-07-05T11:39:03.140296+00:00"},{"alias_kind":"pith_short_16","alias_value":"UN5WEDFOD56VOITU","created_at":"2026-07-05T11:39:03.140296+00:00"},{"alias_kind":"pith_short_8","alias_value":"UN5WEDFO","created_at":"2026-07-05T11:39:03.140296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20433","citing_title":"Kernel Quantile Embeddings and Associated Probability Metrics","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS","json":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS.json","graph_json":"https://pith.science/api/pith-number/UN5WEDFOD56VOITUN26YTOIHGS/graph.json","events_json":"https://pith.science/api/pith-number/UN5WEDFOD56VOITUN26YTOIHGS/events.json","paper":"https://pith.science/paper/UN5WEDFO"},"agent_actions":{"view_html":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS","download_json":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS.json","view_paper":"https://pith.science/paper/UN5WEDFO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15441&json=true","fetch_graph":"https://pith.science/api/pith-number/UN5WEDFOD56VOITUN26YTOIHGS/graph.json","fetch_events":"https://pith.science/api/pith-number/UN5WEDFOD56VOITUN26YTOIHGS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS/action/storage_attestation","attest_author":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS/action/author_attestation","sign_citation":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS/action/citation_signature","submit_replication":"https://pith.science/pith/UN5WEDFOD56VOITUN26YTOIHGS/action/replication_record"}},"created_at":"2026-07-05T11:39:03.140296+00:00","updated_at":"2026-07-05T11:39:03.140296+00:00"}