{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSRRTJ2ZIZXTML7NTAV23U7EQ4","short_pith_number":"pith:CSRRTJ2Z","schema_version":"1.0","canonical_sha256":"14a319a759466f362fed982badd3e48727adcf199d24daf5ec709de4f260363f","source":{"kind":"arxiv","id":"2602.02190","version":2},"attestation_state":"computed","paper":{"title":"PCA of probability measures: Sparse and Dense sampling regimes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elsa Cazelles, Gachon Erell, J\\'er\\'emie Bigot","submitted_at":"2026-02-02T14:56:58Z","abstract_excerpt":"A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from $m$ samples are well understood, the literature has not addressed the setting involving multiple measures. In this paper, we study PCA in a double asymptotic regime where $n$ probability measures are observed, each through $m$ samples. We derive convergence rates of the form $n^{-1/2} + m^{-\\alpha}$ for the empirical covariance operator and the PCA excess risk, where $\\alpha>0"},"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":"2602.02190","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"stat.ML","submitted_at":"2026-02-02T14:56:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"63d32ba623176300dfe4ab9ac2e34cac0a2eb2dc86f82f9b62ea95327ac1b1b9","abstract_canon_sha256":"f6ddc5ea32cbb5f23eed8812d2983a8c19153bc0964adfce6b1ded0b3bc3e697"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:33.924131Z","signature_b64":"UwjirMxVa3IS6nVJ+RmwCeqxV0yKyooYKgFvTJ8cKSEvuc+seTMdaCD7ZJZeJVMUjImTxal0LmNq/7Q3wELLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14a319a759466f362fed982badd3e48727adcf199d24daf5ec709de4f260363f","last_reissued_at":"2026-07-07T02:18:33.923344Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:33.923344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PCA of probability measures: Sparse and Dense sampling regimes","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Elsa Cazelles, Gachon Erell, J\\'er\\'emie Bigot","submitted_at":"2026-02-02T14:56:58Z","abstract_excerpt":"A common approach to perform PCA on probability measures is to embed them into a Hilbert space where standard functional PCA techniques apply. While convergence rates for estimating the embedding of a single measure from $m$ samples are well understood, the literature has not addressed the setting involving multiple measures. In this paper, we study PCA in a double asymptotic regime where $n$ probability measures are observed, each through $m$ samples. We derive convergence rates of the form $n^{-1/2} + m^{-\\alpha}$ for the empirical covariance operator and the PCA excess risk, where $\\alpha>0"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02190","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/2602.02190/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":"2602.02190","created_at":"2026-07-07T02:18:33.923442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02190v2","created_at":"2026-07-07T02:18:33.923442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02190","created_at":"2026-07-07T02:18:33.923442+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSRRTJ2ZIZXT","created_at":"2026-07-07T02:18:33.923442+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSRRTJ2ZIZXTML7N","created_at":"2026-07-07T02:18:33.923442+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSRRTJ2Z","created_at":"2026-07-07T02:18:33.923442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4","json":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4.json","graph_json":"https://pith.science/api/pith-number/CSRRTJ2ZIZXTML7NTAV23U7EQ4/graph.json","events_json":"https://pith.science/api/pith-number/CSRRTJ2ZIZXTML7NTAV23U7EQ4/events.json","paper":"https://pith.science/paper/CSRRTJ2Z"},"agent_actions":{"view_html":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4","download_json":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4.json","view_paper":"https://pith.science/paper/CSRRTJ2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02190&json=true","fetch_graph":"https://pith.science/api/pith-number/CSRRTJ2ZIZXTML7NTAV23U7EQ4/graph.json","fetch_events":"https://pith.science/api/pith-number/CSRRTJ2ZIZXTML7NTAV23U7EQ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4/action/storage_attestation","attest_author":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4/action/author_attestation","sign_citation":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4/action/citation_signature","submit_replication":"https://pith.science/pith/CSRRTJ2ZIZXTML7NTAV23U7EQ4/action/replication_record"}},"created_at":"2026-07-07T02:18:33.923442+00:00","updated_at":"2026-07-07T02:18:33.923442+00:00"}