{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5RBRRGCLBPHK3ARDJUC4I3656S","short_pith_number":"pith:5RBRRGCL","schema_version":"1.0","canonical_sha256":"ec4318984b0bcead82234d05c46fddf492e2dc36ac309634b11b2e81596b17fc","source":{"kind":"arxiv","id":"1810.10815","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Online Learning in Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Shiyin Lu, Zhi-Hua Zhou","submitted_at":"2018-10-25T10:13:04Z","abstract_excerpt":"In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an $O(\\sqrt{T}(1+P_T))$ dynamic regret, where $T$ is the number of iterations and $P_T$ is the path-length of the comparator sequence. However, this result is unsatisfactory, as there exists a large gap from the $\\Omega(\\sqrt{T(1+P_T)})$ lower bound established in our paper. To address this limitation, we develop a novel online method, namely adaptive learning for dynamic environ"},"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":"1810.10815","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-25T10:13:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"538abec013f78f443f7e5c7403fb6636888e359ad55a6009f9c07d92d3f0b147","abstract_canon_sha256":"de2e1d507d88076a385ca2f7809dd361d6a57de9d7fbe3ed882552b3a118c398"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:19.090307Z","signature_b64":"mJiJWFM7I3y0YlWdDyUCmuuCFDDvtuyJFBGTW0wbVnI+mlKkWDDhsa5hQpw44Mmz+bhcuJwxjRCbLeyh3wJHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4318984b0bcead82234d05c46fddf492e2dc36ac309634b11b2e81596b17fc","last_reissued_at":"2026-05-18T00:02:19.089940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:19.089940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Online Learning in Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Lijun Zhang, Shiyin Lu, Zhi-Hua Zhou","submitted_at":"2018-10-25T10:13:04Z","abstract_excerpt":"In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an $O(\\sqrt{T}(1+P_T))$ dynamic regret, where $T$ is the number of iterations and $P_T$ is the path-length of the comparator sequence. However, this result is unsatisfactory, as there exists a large gap from the $\\Omega(\\sqrt{T(1+P_T)})$ lower bound established in our paper. To address this limitation, we develop a novel online method, namely adaptive learning for dynamic environ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10815","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":"1810.10815","created_at":"2026-05-18T00:02:19.089999+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10815v1","created_at":"2026-05-18T00:02:19.089999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10815","created_at":"2026-05-18T00:02:19.089999+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RBRRGCLBPHK","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RBRRGCLBPHK3ARD","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RBRRGCL","created_at":"2026-05-18T12:32:08.215937+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/5RBRRGCLBPHK3ARDJUC4I3656S","json":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S.json","graph_json":"https://pith.science/api/pith-number/5RBRRGCLBPHK3ARDJUC4I3656S/graph.json","events_json":"https://pith.science/api/pith-number/5RBRRGCLBPHK3ARDJUC4I3656S/events.json","paper":"https://pith.science/paper/5RBRRGCL"},"agent_actions":{"view_html":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S","download_json":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S.json","view_paper":"https://pith.science/paper/5RBRRGCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10815&json=true","fetch_graph":"https://pith.science/api/pith-number/5RBRRGCLBPHK3ARDJUC4I3656S/graph.json","fetch_events":"https://pith.science/api/pith-number/5RBRRGCLBPHK3ARDJUC4I3656S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S/action/storage_attestation","attest_author":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S/action/author_attestation","sign_citation":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S/action/citation_signature","submit_replication":"https://pith.science/pith/5RBRRGCLBPHK3ARDJUC4I3656S/action/replication_record"}},"created_at":"2026-05-18T00:02:19.089999+00:00","updated_at":"2026-05-18T00:02:19.089999+00:00"}