{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:DGNOF476VMJCPM5RX5VRDKTLW4","short_pith_number":"pith:DGNOF476","schema_version":"1.0","canonical_sha256":"199ae2f3feab1227b3b1bf6b11aa6bb70d77371ecbcb769966e5a5e2723dccb0","source":{"kind":"arxiv","id":"1501.06225","version":1},"attestation_state":"computed","paper":{"title":"Online Optimization : Competing with Dynamic Comparators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Ali Jadbabaie, Karthik Sridharan, Shahin Shahrampour","submitted_at":"2015-01-26T00:40:08Z","abstract_excerpt":"Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop prediction methods that perform well against complex benchmarks. In this paper, we address these two directions together. We present a fully adaptive method that competes with dynamic benchmarks in which regret guarantee scales with regularity of the sequence of cost functions and comparators. Notably, the regret bound adapts to the smaller complexity measure "},"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":"1501.06225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-01-26T00:40:08Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"a4954cdb3412f5d8b32639afb279e96e44f0270626829e6832550a7ff4bb4de2","abstract_canon_sha256":"afcf5edcbbc276cda1dd1eddf9bd5dbb1428368f82ec15da9ba53716a470fda8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:42.003148Z","signature_b64":"ytmxGem7qzBXxAcP4nzEsJa56ZGZGrFJ7FPqFl8fSeVt/sC5wEfDLK9R25VM9yXvLwpFUkZKGe2BqZK901+eCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"199ae2f3feab1227b3b1bf6b11aa6bb70d77371ecbcb769966e5a5e2723dccb0","last_reissued_at":"2026-05-18T02:28:42.002581Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:42.002581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Optimization : Competing with Dynamic Comparators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Rakhlin, Ali Jadbabaie, Karthik Sridharan, Shahin Shahrampour","submitted_at":"2015-01-26T00:40:08Z","abstract_excerpt":"Recent literature on online learning has focused on developing adaptive algorithms that take advantage of a regularity of the sequence of observations, yet retain worst-case performance guarantees. A complementary direction is to develop prediction methods that perform well against complex benchmarks. In this paper, we address these two directions together. We present a fully adaptive method that competes with dynamic benchmarks in which regret guarantee scales with regularity of the sequence of cost functions and comparators. Notably, the regret bound adapts to the smaller complexity measure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.06225","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":"1501.06225","created_at":"2026-05-18T02:28:42.002665+00:00"},{"alias_kind":"arxiv_version","alias_value":"1501.06225v1","created_at":"2026-05-18T02:28:42.002665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.06225","created_at":"2026-05-18T02:28:42.002665+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGNOF476VMJC","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGNOF476VMJCPM5R","created_at":"2026-05-18T12:29:17.054201+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGNOF476","created_at":"2026-05-18T12:29:17.054201+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/DGNOF476VMJCPM5RX5VRDKTLW4","json":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4.json","graph_json":"https://pith.science/api/pith-number/DGNOF476VMJCPM5RX5VRDKTLW4/graph.json","events_json":"https://pith.science/api/pith-number/DGNOF476VMJCPM5RX5VRDKTLW4/events.json","paper":"https://pith.science/paper/DGNOF476"},"agent_actions":{"view_html":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4","download_json":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4.json","view_paper":"https://pith.science/paper/DGNOF476","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1501.06225&json=true","fetch_graph":"https://pith.science/api/pith-number/DGNOF476VMJCPM5RX5VRDKTLW4/graph.json","fetch_events":"https://pith.science/api/pith-number/DGNOF476VMJCPM5RX5VRDKTLW4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4/action/storage_attestation","attest_author":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4/action/author_attestation","sign_citation":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4/action/citation_signature","submit_replication":"https://pith.science/pith/DGNOF476VMJCPM5RX5VRDKTLW4/action/replication_record"}},"created_at":"2026-05-18T02:28:42.002665+00:00","updated_at":"2026-05-18T02:28:42.002665+00:00"}