{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:TBBMWHAVVQ7KO426SXEPP7QXDR","short_pith_number":"pith:TBBMWHAV","schema_version":"1.0","canonical_sha256":"9842cb1c15ac3ea7735e95c8f7fe171c7a2a0ba0913866827d0a413e2cc39c64","source":{"kind":"arxiv","id":"1207.3012","version":2},"attestation_state":"computed","paper":{"title":"Optimal rates for first-order stochastic convex optimization under Tsybakov noise condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaditya Ramdas, Aarti Singh","submitted_at":"2012-07-12T16:33:49Z","abstract_excerpt":"We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function around its minimizer $x^*_{f,S}$, as quantified by a Tsybakov-like noise condition. Specifically, we prove that if $f$ grows at least as fast as $\\|x-x^*_{f,S}\\|^\\kappa$ around its minimum, for some $\\kappa > 1$, then the optimal rate of learning $f(x^*_{f,S})$ is $\\Theta(T^{-\\frac{\\kappa}{2\\kappa-2}})$. The classic rate $\\Theta(1/\\sqrt T)$ for convex f"},"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":"1207.3012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-07-12T16:33:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e832a1cea458254e3f2649c0b4433f2a6509098a084589053f14a8a2b44071e8","abstract_canon_sha256":"84266ae09b735bb097ae512cc96ee65f93983afaf9ae472d8010d7d296a61673"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:21:08.349403Z","signature_b64":"xcZ6i0oIBtIjB4yORjUZdIFa1siMeBg9WS2z62keZwG0Vg5YFMLm5cFpqWoTUqmQ8sJ/DYMGiy9M4mVdKqRwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9842cb1c15ac3ea7735e95c8f7fe171c7a2a0ba0913866827d0a413e2cc39c64","last_reissued_at":"2026-05-18T02:21:08.348935Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:21:08.348935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal rates for first-order stochastic convex optimization under Tsybakov noise condition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaditya Ramdas, Aarti Singh","submitted_at":"2012-07-12T16:33:49Z","abstract_excerpt":"We focus on the problem of minimizing a convex function $f$ over a convex set $S$ given $T$ queries to a stochastic first order oracle. We argue that the complexity of convex minimization is only determined by the rate of growth of the function around its minimizer $x^*_{f,S}$, as quantified by a Tsybakov-like noise condition. Specifically, we prove that if $f$ grows at least as fast as $\\|x-x^*_{f,S}\\|^\\kappa$ around its minimum, for some $\\kappa > 1$, then the optimal rate of learning $f(x^*_{f,S})$ is $\\Theta(T^{-\\frac{\\kappa}{2\\kappa-2}})$. The classic rate $\\Theta(1/\\sqrt T)$ for convex f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1207.3012","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":""},"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":"1207.3012","created_at":"2026-05-18T02:21:08.348996+00:00"},{"alias_kind":"arxiv_version","alias_value":"1207.3012v2","created_at":"2026-05-18T02:21:08.348996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1207.3012","created_at":"2026-05-18T02:21:08.348996+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBBMWHAVVQ7K","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBBMWHAVVQ7KO426","created_at":"2026-05-18T12:27:23.164592+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBBMWHAV","created_at":"2026-05-18T12:27:23.164592+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04668","citing_title":"Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR","json":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR.json","graph_json":"https://pith.science/api/pith-number/TBBMWHAVVQ7KO426SXEPP7QXDR/graph.json","events_json":"https://pith.science/api/pith-number/TBBMWHAVVQ7KO426SXEPP7QXDR/events.json","paper":"https://pith.science/paper/TBBMWHAV"},"agent_actions":{"view_html":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR","download_json":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR.json","view_paper":"https://pith.science/paper/TBBMWHAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1207.3012&json=true","fetch_graph":"https://pith.science/api/pith-number/TBBMWHAVVQ7KO426SXEPP7QXDR/graph.json","fetch_events":"https://pith.science/api/pith-number/TBBMWHAVVQ7KO426SXEPP7QXDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR/action/storage_attestation","attest_author":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR/action/author_attestation","sign_citation":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR/action/citation_signature","submit_replication":"https://pith.science/pith/TBBMWHAVVQ7KO426SXEPP7QXDR/action/replication_record"}},"created_at":"2026-05-18T02:21:08.348996+00:00","updated_at":"2026-05-18T02:21:08.348996+00:00"}