{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OEWZDSANMWBRP6BC2EV6SPPRVD","short_pith_number":"pith:OEWZDSAN","schema_version":"1.0","canonical_sha256":"712d91c80d658317f822d12be93df1a8ff769086d93eb27405853453b60254d8","source":{"kind":"arxiv","id":"2303.04288","version":2},"attestation_state":"computed","paper":{"title":"Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Christopher Liaw, Hassan Ashtiani, Jamil Arbas","submitted_at":"2023-03-07T23:24:27Z","abstract_excerpt":"We study the problem of privately estimating the parameters of $d$-dimensional Gaussian Mixture Models (GMMs) with $k$ components. For this, we develop a technique to reduce the problem to its non-private counterpart. This allows us to privatize existing non-private algorithms in a blackbox manner, while incurring only a small overhead in the sample complexity and running time. As the main application of our framework, we develop an $(\\varepsilon, \\delta)$-differentially private algorithm to learn GMMs using the non-private algorithm of Moitra and Valiant [MV10] as a blackbox. Consequently, th"},"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":"2303.04288","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2023-03-07T23:24:27Z","cross_cats_sorted":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT"],"title_canon_sha256":"65395f2e01b5e109d1d2a92a7bd8bc756875e3e43c8adf3e1687209ea9a32051","abstract_canon_sha256":"32277e1785a1fd31ae47caffd4b11e52980b098b2d4a278e9f96d93fd275e93d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:38.096719Z","signature_b64":"Iv8+BLxIvUAK9FFL4magEdeqkWgLY8zLx3CRANeJR7BITQvkQqeB/clymKTjkE0L5ALQUyQQhESaIoTS8jLyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"712d91c80d658317f822d12be93df1a8ff769086d93eb27405853453b60254d8","last_reissued_at":"2026-07-05T06:18:38.096191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:38.096191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CR","cs.DS","cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Christopher Liaw, Hassan Ashtiani, Jamil Arbas","submitted_at":"2023-03-07T23:24:27Z","abstract_excerpt":"We study the problem of privately estimating the parameters of $d$-dimensional Gaussian Mixture Models (GMMs) with $k$ components. For this, we develop a technique to reduce the problem to its non-private counterpart. This allows us to privatize existing non-private algorithms in a blackbox manner, while incurring only a small overhead in the sample complexity and running time. As the main application of our framework, we develop an $(\\varepsilon, \\delta)$-differentially private algorithm to learn GMMs using the non-private algorithm of Moitra and Valiant [MV10] as a blackbox. Consequently, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04288","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/2303.04288/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":"2303.04288","created_at":"2026-07-05T06:18:38.096252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.04288v2","created_at":"2026-07-05T06:18:38.096252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04288","created_at":"2026-07-05T06:18:38.096252+00:00"},{"alias_kind":"pith_short_12","alias_value":"OEWZDSANMWBR","created_at":"2026-07-05T06:18:38.096252+00:00"},{"alias_kind":"pith_short_16","alias_value":"OEWZDSANMWBRP6BC","created_at":"2026-07-05T06:18:38.096252+00:00"},{"alias_kind":"pith_short_8","alias_value":"OEWZDSAN","created_at":"2026-07-05T06:18:38.096252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14979","citing_title":"Energy-independent tomography of Gaussian states","ref_index":102,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD","json":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD.json","graph_json":"https://pith.science/api/pith-number/OEWZDSANMWBRP6BC2EV6SPPRVD/graph.json","events_json":"https://pith.science/api/pith-number/OEWZDSANMWBRP6BC2EV6SPPRVD/events.json","paper":"https://pith.science/paper/OEWZDSAN"},"agent_actions":{"view_html":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD","download_json":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD.json","view_paper":"https://pith.science/paper/OEWZDSAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.04288&json=true","fetch_graph":"https://pith.science/api/pith-number/OEWZDSANMWBRP6BC2EV6SPPRVD/graph.json","fetch_events":"https://pith.science/api/pith-number/OEWZDSANMWBRP6BC2EV6SPPRVD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD/action/storage_attestation","attest_author":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD/action/author_attestation","sign_citation":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD/action/citation_signature","submit_replication":"https://pith.science/pith/OEWZDSANMWBRP6BC2EV6SPPRVD/action/replication_record"}},"created_at":"2026-07-05T06:18:38.096252+00:00","updated_at":"2026-07-05T06:18:38.096252+00:00"}