{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KQ42K7GBCX3T7T7MSABVAUGORQ","short_pith_number":"pith:KQ42K7GB","schema_version":"1.0","canonical_sha256":"5439a57cc115f73fcfec90035050ce8c1a8029ca0704c02332af59eb24e08d19","source":{"kind":"arxiv","id":"1905.05917","version":1},"attestation_state":"computed","paper":{"title":"Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guanghui Wang, Lijun Zhang, Shiyin Lu","submitted_at":"2019-05-15T02:29:21Z","abstract_excerpt":"In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are optimal for only a subclass of loss functions. To address this limitation, we propose a novel online method, namely Maler, which enjoys the optimal $O(\\sqrt{T})$, $O(d\\log T)$ and $O(\\log T)$ regret bounds for general convex, exponentially concave, and strongly convex functions respectively. The essential idea is to run multiple types of learning alg"},"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":"1905.05917","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T02:29:21Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"20dc0ce52ae99e614babb540fd53e01ef8daae6961202b31bb51f84471c7ad8c","abstract_canon_sha256":"8694f43ed6ece4fc93172eb84aed7d630fe65b04113b8b2f9588da521325e04d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:08.112819Z","signature_b64":"nM8/fonXceCVxYwmoMIl2pVHlhK86KDGhIum+a1vvYilO1VTRRS1iNQ3U35iYVbh1wYYizyDbRiuHL7NlzwkBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5439a57cc115f73fcfec90035050ce8c1a8029ca0704c02332af59eb24e08d19","last_reissued_at":"2026-05-17T23:46:08.112091Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:08.112091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guanghui Wang, Lijun Zhang, Shiyin Lu","submitted_at":"2019-05-15T02:29:21Z","abstract_excerpt":"In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are optimal for only a subclass of loss functions. To address this limitation, we propose a novel online method, namely Maler, which enjoys the optimal $O(\\sqrt{T})$, $O(d\\log T)$ and $O(\\log T)$ regret bounds for general convex, exponentially concave, and strongly convex functions respectively. The essential idea is to run multiple types of learning alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05917","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":"1905.05917","created_at":"2026-05-17T23:46:08.112211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.05917v1","created_at":"2026-05-17T23:46:08.112211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05917","created_at":"2026-05-17T23:46:08.112211+00:00"},{"alias_kind":"pith_short_12","alias_value":"KQ42K7GBCX3T","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KQ42K7GBCX3T7T7M","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KQ42K7GB","created_at":"2026-05-18T12:33:21.387695+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/KQ42K7GBCX3T7T7MSABVAUGORQ","json":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ.json","graph_json":"https://pith.science/api/pith-number/KQ42K7GBCX3T7T7MSABVAUGORQ/graph.json","events_json":"https://pith.science/api/pith-number/KQ42K7GBCX3T7T7MSABVAUGORQ/events.json","paper":"https://pith.science/paper/KQ42K7GB"},"agent_actions":{"view_html":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ","download_json":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ.json","view_paper":"https://pith.science/paper/KQ42K7GB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.05917&json=true","fetch_graph":"https://pith.science/api/pith-number/KQ42K7GBCX3T7T7MSABVAUGORQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KQ42K7GBCX3T7T7MSABVAUGORQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ/action/storage_attestation","attest_author":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ/action/author_attestation","sign_citation":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ/action/citation_signature","submit_replication":"https://pith.science/pith/KQ42K7GBCX3T7T7MSABVAUGORQ/action/replication_record"}},"created_at":"2026-05-17T23:46:08.112211+00:00","updated_at":"2026-05-17T23:46:08.112211+00:00"}