{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FHZYW6KVMLC4WJFFBUVMZVDEP3","short_pith_number":"pith:FHZYW6KV","schema_version":"1.0","canonical_sha256":"29f38b795562c5cb24a50d2accd4647efcc5bc187b1acd079032098333426553","source":{"kind":"arxiv","id":"1802.10575","version":2},"attestation_state":"computed","paper":{"title":"Near-Optimal Sample Complexity Bounds for Maximum Likelihood Estimation of Multivariate Log-concave Densities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Alistair Stewart, Anastasios Sidiropoulos, Ilias Diakonikolas, Timothy Carpenter","submitted_at":"2018-02-28T18:32:07Z","abstract_excerpt":"We study the problem of learning multivariate log-concave densities with respect to a global loss function. We obtain the first upper bound on the sample complexity of the maximum likelihood estimator (MLE) for a log-concave density on $\\mathbb{R}^d$, for all $d \\geq 4$. Prior to this work, no finite sample upper bound was known for this estimator in more than $3$ dimensions.\n  In more detail, we prove that for any $d \\geq 1$ and $\\epsilon>0$, given $\\tilde{O}_d((1/\\epsilon)^{(d+3)/2})$ samples drawn from an unknown log-concave density $f_0$ on $\\mathbb{R}^d$, the MLE outputs a hypothesis $h$ "},"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":"1802.10575","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2018-02-28T18:32:07Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT","stat.TH"],"title_canon_sha256":"1c9308f141cfa8f54df5aeaf59a13c983bf78b0e6abbbf7a4107745aba10e3ba","abstract_canon_sha256":"8de42f7913e0b62786cc27f7574cb21c639fc53eb1a4995199bfb48f4ca9e21e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:01.902274Z","signature_b64":"LS0Ha1TFNfUWy/jZ8aYSkUNeZCqSD2VPE+gKQvecFElD1UascYPaJ77LSs0necXNYu3ZMXOSk9DIKEyu4Py/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29f38b795562c5cb24a50d2accd4647efcc5bc187b1acd079032098333426553","last_reissued_at":"2026-05-17T23:59:01.901678Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:01.901678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Sample Complexity Bounds for Maximum Likelihood Estimation of Multivariate Log-concave Densities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT","stat.TH"],"primary_cat":"math.ST","authors_text":"Alistair Stewart, Anastasios Sidiropoulos, Ilias Diakonikolas, Timothy Carpenter","submitted_at":"2018-02-28T18:32:07Z","abstract_excerpt":"We study the problem of learning multivariate log-concave densities with respect to a global loss function. We obtain the first upper bound on the sample complexity of the maximum likelihood estimator (MLE) for a log-concave density on $\\mathbb{R}^d$, for all $d \\geq 4$. Prior to this work, no finite sample upper bound was known for this estimator in more than $3$ dimensions.\n  In more detail, we prove that for any $d \\geq 1$ and $\\epsilon>0$, given $\\tilde{O}_d((1/\\epsilon)^{(d+3)/2})$ samples drawn from an unknown log-concave density $f_0$ on $\\mathbb{R}^d$, the MLE outputs a hypothesis $h$ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.10575","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":""},"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":"1802.10575","created_at":"2026-05-17T23:59:01.901791+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.10575v2","created_at":"2026-05-17T23:59:01.901791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.10575","created_at":"2026-05-17T23:59:01.901791+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHZYW6KVMLC4","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHZYW6KVMLC4WJFF","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHZYW6KV","created_at":"2026-05-18T12:32:22.470017+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/FHZYW6KVMLC4WJFFBUVMZVDEP3","json":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3.json","graph_json":"https://pith.science/api/pith-number/FHZYW6KVMLC4WJFFBUVMZVDEP3/graph.json","events_json":"https://pith.science/api/pith-number/FHZYW6KVMLC4WJFFBUVMZVDEP3/events.json","paper":"https://pith.science/paper/FHZYW6KV"},"agent_actions":{"view_html":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3","download_json":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3.json","view_paper":"https://pith.science/paper/FHZYW6KV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.10575&json=true","fetch_graph":"https://pith.science/api/pith-number/FHZYW6KVMLC4WJFFBUVMZVDEP3/graph.json","fetch_events":"https://pith.science/api/pith-number/FHZYW6KVMLC4WJFFBUVMZVDEP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3/action/storage_attestation","attest_author":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3/action/author_attestation","sign_citation":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3/action/citation_signature","submit_replication":"https://pith.science/pith/FHZYW6KVMLC4WJFFBUVMZVDEP3/action/replication_record"}},"created_at":"2026-05-17T23:59:01.901791+00:00","updated_at":"2026-05-17T23:59:01.901791+00:00"}