{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DCOGMCELVAGYBSP7RYQIK2VP4C","short_pith_number":"pith:DCOGMCEL","schema_version":"1.0","canonical_sha256":"189c66088ba80d80c9ff8e20856aafe0aef4d2e0e4dfbbe92ceb92757b3c0d05","source":{"kind":"arxiv","id":"1809.03073","version":1},"attestation_state":"computed","paper":{"title":"Sample Complexity of Nonparametric Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Bryon Aragam, Chen Dan, Eric P. Xing, Liu Leqi, Pradeep Ravikumar","submitted_at":"2018-09-10T01:12:26Z","abstract_excerpt":"We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions. Under these assumptions, we establish an $\\Omega(K\\log K)$ labeled sample complexity bound without imposing parametric assumptions, where $K$ is the number of classes. Our results suggest that even in nonparametric settings it is possible to learn a near-optimal classifier using only a few labeled samples. Unlike previous theoretical work which"},"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":"1809.03073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-10T01:12:26Z","cross_cats_sorted":["cs.AI","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"e90f73a563958ed770f133bfa703c7be889781c2de55c018fc60d3b839e20227","abstract_canon_sha256":"215c71ef9af97d646d59b916e415449f80d396d04fda46cce94fc5471ec9c84d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:10.148374Z","signature_b64":"ucsOw5dYtImbP0OGSdvD/72qNlRuV53dx4nWxaQegTQLIM9kdC4e9l1AYWwnbrGVobnJ5Yd5X+u0v1JBuMvCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"189c66088ba80d80c9ff8e20856aafe0aef4d2e0e4dfbbe92ceb92757b3c0d05","last_reissued_at":"2026-05-18T00:06:10.147731Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:10.147731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Nonparametric Semi-Supervised Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Bryon Aragam, Chen Dan, Eric P. Xing, Liu Leqi, Pradeep Ravikumar","submitted_at":"2018-09-10T01:12:26Z","abstract_excerpt":"We study the sample complexity of semi-supervised learning (SSL) and introduce new assumptions based on the mismatch between a mixture model learned from unlabeled data and the true mixture model induced by the (unknown) class conditional distributions. Under these assumptions, we establish an $\\Omega(K\\log K)$ labeled sample complexity bound without imposing parametric assumptions, where $K$ is the number of classes. Our results suggest that even in nonparametric settings it is possible to learn a near-optimal classifier using only a few labeled samples. Unlike previous theoretical work which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.03073","kind":"arxiv","version":1},"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":"1809.03073","created_at":"2026-05-18T00:06:10.147830+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.03073v1","created_at":"2026-05-18T00:06:10.147830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.03073","created_at":"2026-05-18T00:06:10.147830+00:00"},{"alias_kind":"pith_short_12","alias_value":"DCOGMCELVAGY","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DCOGMCELVAGYBSP7","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DCOGMCEL","created_at":"2026-05-18T12:32:19.392346+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/DCOGMCELVAGYBSP7RYQIK2VP4C","json":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C.json","graph_json":"https://pith.science/api/pith-number/DCOGMCELVAGYBSP7RYQIK2VP4C/graph.json","events_json":"https://pith.science/api/pith-number/DCOGMCELVAGYBSP7RYQIK2VP4C/events.json","paper":"https://pith.science/paper/DCOGMCEL"},"agent_actions":{"view_html":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C","download_json":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C.json","view_paper":"https://pith.science/paper/DCOGMCEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.03073&json=true","fetch_graph":"https://pith.science/api/pith-number/DCOGMCELVAGYBSP7RYQIK2VP4C/graph.json","fetch_events":"https://pith.science/api/pith-number/DCOGMCELVAGYBSP7RYQIK2VP4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C/action/storage_attestation","attest_author":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C/action/author_attestation","sign_citation":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C/action/citation_signature","submit_replication":"https://pith.science/pith/DCOGMCELVAGYBSP7RYQIK2VP4C/action/replication_record"}},"created_at":"2026-05-18T00:06:10.147830+00:00","updated_at":"2026-05-18T00:06:10.147830+00:00"}