{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:GYXBD4SN7ULO7MVIGSMCPOUSB4","short_pith_number":"pith:GYXBD4SN","schema_version":"1.0","canonical_sha256":"362e11f24dfd16efb2a8349827ba920f05fe93c51dd9b890ed49c8294ee96364","source":{"kind":"arxiv","id":"1706.01596","version":3},"attestation_state":"computed","paper":{"title":"Sample-Efficient Learning of Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbas Mehrabian, Hassan Ashtiani, Shai Ben-David","submitted_at":"2017-06-06T03:47:28Z","abstract_excerpt":"We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown target distribution, and want to output a distribution that is close to the target in total variation distance. Let $\\mathcal F$ be an arbitrary class of probability distributions, and let $\\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\\mathcal F$. Assuming the existence of a method for learning $\\mathcal F$ with sample complexity $m_{\\mathcal{F}}(\\epsilon)$, we provide a method for learning $\\mathcal F^k$ with sample complexity $O({"},"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":"1706.01596","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-06T03:47:28Z","cross_cats_sorted":[],"title_canon_sha256":"fd45babd234a0b54a9b4edb45ba2f1321d65b2cdd2ec60d03e21012922d8e973","abstract_canon_sha256":"21c5c331c6dac170bcc3211d53026de893e4bf9deb17fd28b52682514ae4fc74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:22.555089Z","signature_b64":"f0D99IJ4LFX8p7FDN2YNOi0I5t8unsORzXmf/XmIA1F3YC+tOlSU85YC1P3pSZ2tePUJE7dVrLzDJBi/ECKFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362e11f24dfd16efb2a8349827ba920f05fe93c51dd9b890ed49c8294ee96364","last_reissued_at":"2026-05-18T00:14:22.554617Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:22.554617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Learning of Mixtures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Abbas Mehrabian, Hassan Ashtiani, Shai Ben-David","submitted_at":"2017-06-06T03:47:28Z","abstract_excerpt":"We consider PAC learning of probability distributions (a.k.a. density estimation), where we are given an i.i.d. sample generated from an unknown target distribution, and want to output a distribution that is close to the target in total variation distance. Let $\\mathcal F$ be an arbitrary class of probability distributions, and let $\\mathcal{F}^k$ denote the class of $k$-mixtures of elements of $\\mathcal F$. Assuming the existence of a method for learning $\\mathcal F$ with sample complexity $m_{\\mathcal{F}}(\\epsilon)$, we provide a method for learning $\\mathcal F^k$ with sample complexity $O({"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01596","kind":"arxiv","version":3},"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":"1706.01596","created_at":"2026-05-18T00:14:22.554681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01596v3","created_at":"2026-05-18T00:14:22.554681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01596","created_at":"2026-05-18T00:14:22.554681+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYXBD4SN7ULO","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYXBD4SN7ULO7MVI","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYXBD4SN","created_at":"2026-05-18T12:31:18.294218+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/GYXBD4SN7ULO7MVIGSMCPOUSB4","json":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4.json","graph_json":"https://pith.science/api/pith-number/GYXBD4SN7ULO7MVIGSMCPOUSB4/graph.json","events_json":"https://pith.science/api/pith-number/GYXBD4SN7ULO7MVIGSMCPOUSB4/events.json","paper":"https://pith.science/paper/GYXBD4SN"},"agent_actions":{"view_html":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4","download_json":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4.json","view_paper":"https://pith.science/paper/GYXBD4SN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01596&json=true","fetch_graph":"https://pith.science/api/pith-number/GYXBD4SN7ULO7MVIGSMCPOUSB4/graph.json","fetch_events":"https://pith.science/api/pith-number/GYXBD4SN7ULO7MVIGSMCPOUSB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4/action/storage_attestation","attest_author":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4/action/author_attestation","sign_citation":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4/action/citation_signature","submit_replication":"https://pith.science/pith/GYXBD4SN7ULO7MVIGSMCPOUSB4/action/replication_record"}},"created_at":"2026-05-18T00:14:22.554681+00:00","updated_at":"2026-05-18T00:14:22.554681+00:00"}