{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RZM2W7UX5PEPKSYNX2RZHOH7LR","short_pith_number":"pith:RZM2W7UX","schema_version":"1.0","canonical_sha256":"8e59ab7e97ebc8f54b0dbea393b8ff5c48fe6cfe5f26965634e4a261b745a273","source":{"kind":"arxiv","id":"2110.08418","version":2},"attestation_state":"computed","paper":{"title":"Nuances in Margin Conditions Determine Gains in Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gan Yuan, Samory Kpotufe, Yunfan Zhao","submitted_at":"2021-10-16T00:17:39Z","abstract_excerpt":"We consider nonparametric classification with smooth regression functions, where it is well known that notions of margin in $E[Y|X]$ determine fast or slow rates in both active and passive learning. Here we elucidate a striking distinction between the two settings. Namely, we show that some seemingly benign nuances in notions of margin -- involving the uniqueness of the Bayes classifier, and which have no apparent effect on rates in passive learning -- determine whether or not any active learner can outperform passive learning rates. In particular, for Audibert-Tsybakov's margin condition (all"},"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":"2110.08418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-10-16T00:17:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"52fb1a3626c004194019caac47de6693ff9f9a67dc1390344472d67f7a195640","abstract_canon_sha256":"e09a4cc9569022f60fffc7fffe23570dfae6f8ed8cd948109d88ec1b3fb4ea3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:00:19.012684Z","signature_b64":"g2u2P4R7g7G8i/h2HoxgGtj0jHF9kORMWcjM57ZM9zbEW8XcbANxekRVmg3hwhmEY22Haz0Ls5/1wQLxZtunDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e59ab7e97ebc8f54b0dbea393b8ff5c48fe6cfe5f26965634e4a261b745a273","last_reissued_at":"2026-07-05T04:00:19.012288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:00:19.012288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nuances in Margin Conditions Determine Gains in Active Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gan Yuan, Samory Kpotufe, Yunfan Zhao","submitted_at":"2021-10-16T00:17:39Z","abstract_excerpt":"We consider nonparametric classification with smooth regression functions, where it is well known that notions of margin in $E[Y|X]$ determine fast or slow rates in both active and passive learning. Here we elucidate a striking distinction between the two settings. Namely, we show that some seemingly benign nuances in notions of margin -- involving the uniqueness of the Bayes classifier, and which have no apparent effect on rates in passive learning -- determine whether or not any active learner can outperform passive learning rates. In particular, for Audibert-Tsybakov's margin condition (all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08418","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/2110.08418/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":"2110.08418","created_at":"2026-07-05T04:00:19.012356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08418v2","created_at":"2026-07-05T04:00:19.012356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08418","created_at":"2026-07-05T04:00:19.012356+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZM2W7UX5PEP","created_at":"2026-07-05T04:00:19.012356+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZM2W7UX5PEPKSYN","created_at":"2026-07-05T04:00:19.012356+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZM2W7UX","created_at":"2026-07-05T04:00:19.012356+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/RZM2W7UX5PEPKSYNX2RZHOH7LR","json":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR.json","graph_json":"https://pith.science/api/pith-number/RZM2W7UX5PEPKSYNX2RZHOH7LR/graph.json","events_json":"https://pith.science/api/pith-number/RZM2W7UX5PEPKSYNX2RZHOH7LR/events.json","paper":"https://pith.science/paper/RZM2W7UX"},"agent_actions":{"view_html":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR","download_json":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR.json","view_paper":"https://pith.science/paper/RZM2W7UX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08418&json=true","fetch_graph":"https://pith.science/api/pith-number/RZM2W7UX5PEPKSYNX2RZHOH7LR/graph.json","fetch_events":"https://pith.science/api/pith-number/RZM2W7UX5PEPKSYNX2RZHOH7LR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR/action/storage_attestation","attest_author":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR/action/author_attestation","sign_citation":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR/action/citation_signature","submit_replication":"https://pith.science/pith/RZM2W7UX5PEPKSYNX2RZHOH7LR/action/replication_record"}},"created_at":"2026-07-05T04:00:19.012356+00:00","updated_at":"2026-07-05T04:00:19.012356+00:00"}