{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A67EUXRDZ3MPQV5Q6VDWF23HSF","short_pith_number":"pith:A67EUXRD","schema_version":"1.0","canonical_sha256":"07be4a5e23ced8f857b0f54762eb67914e2faf03afc9a1b1c823ffbb974123fa","source":{"kind":"arxiv","id":"2404.18869","version":2},"attestation_state":"computed","paper":{"title":"Learning Mixtures of Gaussians Using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Holden Lee, Jonathan Kelner, Khashayar Gatmiry","submitted_at":"2024-04-29T17:00:20Z","abstract_excerpt":"We give a new algorithm for learning mixtures of $k$ Gaussians (with identity covariance in $\\mathbb{R}^n$) to TV error $\\varepsilon$, with quasi-polynomial ($O(n^{\\text{poly\\,log}\\left(\\frac{n+k}{\\varepsilon}\\right)})$) time and sample complexity, under a minimum weight assumption. Our results extend to continuous mixtures of Gaussians where the mixing distribution is supported on a union of $k$ balls of constant radius. In particular, this applies to the case of Gaussian convolutions of distributions on low-dimensional manifolds, or more generally sets with small covering number, for which n"},"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":"2404.18869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-29T17:00:20Z","cross_cats_sorted":["cs.DS","math.PR","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"50f4c831d95f21a3b22447ec155c2c373508291e8c4958fddf6e9005e6770ba7","abstract_canon_sha256":"80ecd76bcb8ed510b42b51dfcd80a24cb5761e043396cc9bb665938db39d8b58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:53.396134Z","signature_b64":"pQJFoNCIftVSPXLBqWVvRyb8UIzmYshuCHFOYvY1QMbmkOcqSNew7VzEzhd4kQvNaj+msGcpnsxVwuEWqzx1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07be4a5e23ced8f857b0f54762eb67914e2faf03afc9a1b1c823ffbb974123fa","last_reissued_at":"2026-07-05T10:23:53.395229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:53.395229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Mixtures of Gaussians Using Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.PR","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Holden Lee, Jonathan Kelner, Khashayar Gatmiry","submitted_at":"2024-04-29T17:00:20Z","abstract_excerpt":"We give a new algorithm for learning mixtures of $k$ Gaussians (with identity covariance in $\\mathbb{R}^n$) to TV error $\\varepsilon$, with quasi-polynomial ($O(n^{\\text{poly\\,log}\\left(\\frac{n+k}{\\varepsilon}\\right)})$) time and sample complexity, under a minimum weight assumption. Our results extend to continuous mixtures of Gaussians where the mixing distribution is supported on a union of $k$ balls of constant radius. In particular, this applies to the case of Gaussian convolutions of distributions on low-dimensional manifolds, or more generally sets with small covering number, for which n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18869","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/2404.18869/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":"2404.18869","created_at":"2026-07-05T10:23:53.395367+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18869v2","created_at":"2026-07-05T10:23:53.395367+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18869","created_at":"2026-07-05T10:23:53.395367+00:00"},{"alias_kind":"pith_short_12","alias_value":"A67EUXRDZ3MP","created_at":"2026-07-05T10:23:53.395367+00:00"},{"alias_kind":"pith_short_16","alias_value":"A67EUXRDZ3MPQV5Q","created_at":"2026-07-05T10:23:53.395367+00:00"},{"alias_kind":"pith_short_8","alias_value":"A67EUXRD","created_at":"2026-07-05T10:23:53.395367+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03820","citing_title":"A Quantitative Approximation Framework for Flow Distillation in Diffusion Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21911","citing_title":"Noise Schedule Design for Diffusion Models: An Optimal Control Perspective","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11311","citing_title":"Couple to Control: Joint Initial Noise Design in Diffusion Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10019","citing_title":"The two clocks and the innovation window: When and how generative models learn rules","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF","json":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF.json","graph_json":"https://pith.science/api/pith-number/A67EUXRDZ3MPQV5Q6VDWF23HSF/graph.json","events_json":"https://pith.science/api/pith-number/A67EUXRDZ3MPQV5Q6VDWF23HSF/events.json","paper":"https://pith.science/paper/A67EUXRD"},"agent_actions":{"view_html":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF","download_json":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF.json","view_paper":"https://pith.science/paper/A67EUXRD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18869&json=true","fetch_graph":"https://pith.science/api/pith-number/A67EUXRDZ3MPQV5Q6VDWF23HSF/graph.json","fetch_events":"https://pith.science/api/pith-number/A67EUXRDZ3MPQV5Q6VDWF23HSF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF/action/storage_attestation","attest_author":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF/action/author_attestation","sign_citation":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF/action/citation_signature","submit_replication":"https://pith.science/pith/A67EUXRDZ3MPQV5Q6VDWF23HSF/action/replication_record"}},"created_at":"2026-07-05T10:23:53.395367+00:00","updated_at":"2026-07-05T10:23:53.395367+00:00"}