{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O4ZMIHXRJAYYVVIORFNWW2LJK3","short_pith_number":"pith:O4ZMIHXR","schema_version":"1.0","canonical_sha256":"7732c41ef148318ad50e895b6b696956c739ea0cfef074c6a3a30acbd64d3e54","source":{"kind":"arxiv","id":"2404.18893","version":2},"attestation_state":"computed","paper":{"title":"Learning general Gaussian mixtures with efficient score matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Kulin Shah, Sitan Chen, Vasilis Kontonis","submitted_at":"2024-04-29T17:30:36Z","abstract_excerpt":"We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covariance matrices have bounded condition number and that the means and covariances lie in a ball of bounded radius. We give an algorithm that draws $d^{\\mathrm{poly}(k/\\varepsilon)}$ samples from the target mixture, runs in sample-polynomial time, and constructs a sampler whose output distribution is $\\varepsilon$-far from the unknown mixture in total variation. Prior works for this problem either (i) required exponenti"},"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":"2404.18893","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DS","submitted_at":"2024-04-29T17:30:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"62977abad74df01e65750823d5418bfd42ed7a8a10549dcf9da1b87ed8934a90","abstract_canon_sha256":"b1dd7a057b2d8607bb04019d5573a1256783dbcb33640e384d1d0e51679a67c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:37:07.753756Z","signature_b64":"Z7loaLJrrIVl35pDAUseGXf2Iuy2u3Z/8R1dLXjkMT3dLTZiB/CHlIBHumO/74iauFRiSKtbyfItiKIp1zATDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7732c41ef148318ad50e895b6b696956c739ea0cfef074c6a3a30acbd64d3e54","last_reissued_at":"2026-07-05T09:37:07.753270Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:37:07.753270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning general Gaussian mixtures with efficient score matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DS","authors_text":"Kulin Shah, Sitan Chen, Vasilis Kontonis","submitted_at":"2024-04-29T17:30:36Z","abstract_excerpt":"We study the problem of learning mixtures of $k$ Gaussians in $d$ dimensions. We make no separation assumptions on the underlying mixture components: we only require that the covariance matrices have bounded condition number and that the means and covariances lie in a ball of bounded radius. We give an algorithm that draws $d^{\\mathrm{poly}(k/\\varepsilon)}$ samples from the target mixture, runs in sample-polynomial time, and constructs a sampler whose output distribution is $\\varepsilon$-far from the unknown mixture in total variation. Prior works for this problem either (i) required exponenti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18893","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/2404.18893/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":"2404.18893","created_at":"2026-07-05T09:37:07.753327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18893v2","created_at":"2026-07-05T09:37:07.753327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18893","created_at":"2026-07-05T09:37:07.753327+00:00"},{"alias_kind":"pith_short_12","alias_value":"O4ZMIHXRJAYY","created_at":"2026-07-05T09:37:07.753327+00:00"},{"alias_kind":"pith_short_16","alias_value":"O4ZMIHXRJAYYVVIO","created_at":"2026-07-05T09:37:07.753327+00:00"},{"alias_kind":"pith_short_8","alias_value":"O4ZMIHXR","created_at":"2026-07-05T09:37:07.753327+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19876","citing_title":"Global Convergence of Gradient Descent for Score Matching in Gaussian Mixtures via Reverse Fisher Divergence","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22950","citing_title":"Diffusion-based Denoising Beats Vanilla Score Matching in Parameter Estimation: A Theoretical Explanation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21911","citing_title":"Noise Schedule Design for Diffusion Models: An Optimal Control Perspective","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3","json":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3.json","graph_json":"https://pith.science/api/pith-number/O4ZMIHXRJAYYVVIORFNWW2LJK3/graph.json","events_json":"https://pith.science/api/pith-number/O4ZMIHXRJAYYVVIORFNWW2LJK3/events.json","paper":"https://pith.science/paper/O4ZMIHXR"},"agent_actions":{"view_html":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3","download_json":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3.json","view_paper":"https://pith.science/paper/O4ZMIHXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18893&json=true","fetch_graph":"https://pith.science/api/pith-number/O4ZMIHXRJAYYVVIORFNWW2LJK3/graph.json","fetch_events":"https://pith.science/api/pith-number/O4ZMIHXRJAYYVVIORFNWW2LJK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3/action/storage_attestation","attest_author":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3/action/author_attestation","sign_citation":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3/action/citation_signature","submit_replication":"https://pith.science/pith/O4ZMIHXRJAYYVVIORFNWW2LJK3/action/replication_record"}},"created_at":"2026-07-05T09:37:07.753327+00:00","updated_at":"2026-07-05T09:37:07.753327+00:00"}