{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:PZ2KELCFZMNSK5EHHFL3WCZRIO","short_pith_number":"pith:PZ2KELCF","schema_version":"1.0","canonical_sha256":"7e74a22c45cb1b2574873957bb0b31438b929400c37a3f7070abc94c679175bb","source":{"kind":"arxiv","id":"2112.14368","version":3},"attestation_state":"computed","paper":{"title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Peng Zhao, Yu-Jie Zhang, Zhi-Hua Zhou","submitted_at":"2021-12-29T02:42:59Z","abstract_excerpt":"We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence. Let $T$ be the time horizon and $P_T$ be the path length that essentially reflects the non-stationarity of environments, the state-of-the-art dynamic regret is $\\mathcal{O}(\\sqrt{T(1+P_T)})$. Although this bound is proved to be minimax optimal for convex functions, in this paper, we demonstrate that it is possible to further enhance the guara"},"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":"2112.14368","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-29T02:42:59Z","cross_cats_sorted":[],"title_canon_sha256":"02c038462f0ce32952d6d66733f45863adab6f1348a1b36918608322536a9099","abstract_canon_sha256":"eb407309b5f6113efb032bae26dcf26b91ddc3f9c61cb35151d40ee8840b047c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:53.973532Z","signature_b64":"smdbrhf67UHlFG8OFWYL9d9j+kzG1qpqRLbp2A8n7UYCBaiF4gA8ycg0+D3IP5deDR/YhSz6RUtbhBvjWUBQAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e74a22c45cb1b2574873957bb0b31438b929400c37a3f7070abc94c679175bb","last_reissued_at":"2026-07-05T08:04:53.973047Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:53.973047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Peng Zhao, Yu-Jie Zhang, Zhi-Hua Zhou","submitted_at":"2021-12-29T02:42:59Z","abstract_excerpt":"We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible comparator sequence. Let $T$ be the time horizon and $P_T$ be the path length that essentially reflects the non-stationarity of environments, the state-of-the-art dynamic regret is $\\mathcal{O}(\\sqrt{T(1+P_T)})$. Although this bound is proved to be minimax optimal for convex functions, in this paper, we demonstrate that it is possible to further enhance the guara"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.14368","kind":"arxiv","version":3},"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/2112.14368/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":"2112.14368","created_at":"2026-07-05T08:04:53.973103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.14368v3","created_at":"2026-07-05T08:04:53.973103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.14368","created_at":"2026-07-05T08:04:53.973103+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZ2KELCFZMNS","created_at":"2026-07-05T08:04:53.973103+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZ2KELCFZMNSK5EH","created_at":"2026-07-05T08:04:53.973103+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZ2KELCF","created_at":"2026-07-05T08:04:53.973103+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29092","citing_title":"Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO","json":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO.json","graph_json":"https://pith.science/api/pith-number/PZ2KELCFZMNSK5EHHFL3WCZRIO/graph.json","events_json":"https://pith.science/api/pith-number/PZ2KELCFZMNSK5EHHFL3WCZRIO/events.json","paper":"https://pith.science/paper/PZ2KELCF"},"agent_actions":{"view_html":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO","download_json":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO.json","view_paper":"https://pith.science/paper/PZ2KELCF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.14368&json=true","fetch_graph":"https://pith.science/api/pith-number/PZ2KELCFZMNSK5EHHFL3WCZRIO/graph.json","fetch_events":"https://pith.science/api/pith-number/PZ2KELCFZMNSK5EHHFL3WCZRIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO/action/storage_attestation","attest_author":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO/action/author_attestation","sign_citation":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO/action/citation_signature","submit_replication":"https://pith.science/pith/PZ2KELCFZMNSK5EHHFL3WCZRIO/action/replication_record"}},"created_at":"2026-07-05T08:04:53.973103+00:00","updated_at":"2026-07-05T08:04:53.973103+00:00"}