{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2WUHFGN4JA2MGEWFCWAUHPDCUR","short_pith_number":"pith:2WUHFGN4","schema_version":"1.0","canonical_sha256":"d5a87299bc4834c312c5158143bc62a44bdd7f3cdc5cd8c2931a4c782797db36","source":{"kind":"arxiv","id":"1810.10132","version":2},"attestation_state":"computed","paper":{"title":"Smoothed Online Optimization for Regression and Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Gautam Goel","submitted_at":"2018-10-23T23:57:40Z","abstract_excerpt":"We consider Online Convex Optimization (OCO) in the setting where the costs are $m$-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio $3 + O(1/m)$, irrespective of the ambient dimension. Additionally, we show that when the sequence of cost functions is $\\epsilon$-smooth, OBD has near-optimal dynamic regret and maintains strong per-round accuracy. We demonstrate the generality of our approach by showing that "},"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":"1810.10132","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-23T23:57:40Z","cross_cats_sorted":["cs.DS","math.OC","stat.ML"],"title_canon_sha256":"20dc37796f41ec922aa7535d6723362f7ff71116d90b02d0a3d35477c18c72cd","abstract_canon_sha256":"2cb0856fd143a6429d72e105694f6bff763c2c42b2fde6742070db0a68962555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:27.512901Z","signature_b64":"yLbVCkL1Idx64rubHyByHi9KRWPGmImbrsarSs6Rn7f0ttHvD4cU0fdk0Q874lFKif7iuF9ObV5X7BM1+IPFCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5a87299bc4834c312c5158143bc62a44bdd7f3cdc5cd8c2931a4c782797db36","last_reissued_at":"2026-05-17T23:49:27.512370Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:27.512370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Smoothed Online Optimization for Regression and Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Wierman, Gautam Goel","submitted_at":"2018-10-23T23:57:40Z","abstract_excerpt":"We consider Online Convex Optimization (OCO) in the setting where the costs are $m$-strongly convex and the online learner pays a switching cost for changing decisions between rounds. We show that the recently proposed Online Balanced Descent (OBD) algorithm is constant competitive in this setting, with competitive ratio $3 + O(1/m)$, irrespective of the ambient dimension. Additionally, we show that when the sequence of cost functions is $\\epsilon$-smooth, OBD has near-optimal dynamic regret and maintains strong per-round accuracy. We demonstrate the generality of our approach by showing that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10132","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":"1810.10132","created_at":"2026-05-17T23:49:27.512459+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10132v2","created_at":"2026-05-17T23:49:27.512459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10132","created_at":"2026-05-17T23:49:27.512459+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WUHFGN4JA2M","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WUHFGN4JA2MGEWF","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WUHFGN4","created_at":"2026-05-18T12:32:02.567920+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/2WUHFGN4JA2MGEWFCWAUHPDCUR","json":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR.json","graph_json":"https://pith.science/api/pith-number/2WUHFGN4JA2MGEWFCWAUHPDCUR/graph.json","events_json":"https://pith.science/api/pith-number/2WUHFGN4JA2MGEWFCWAUHPDCUR/events.json","paper":"https://pith.science/paper/2WUHFGN4"},"agent_actions":{"view_html":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR","download_json":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR.json","view_paper":"https://pith.science/paper/2WUHFGN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10132&json=true","fetch_graph":"https://pith.science/api/pith-number/2WUHFGN4JA2MGEWFCWAUHPDCUR/graph.json","fetch_events":"https://pith.science/api/pith-number/2WUHFGN4JA2MGEWFCWAUHPDCUR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR/action/storage_attestation","attest_author":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR/action/author_attestation","sign_citation":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR/action/citation_signature","submit_replication":"https://pith.science/pith/2WUHFGN4JA2MGEWFCWAUHPDCUR/action/replication_record"}},"created_at":"2026-05-17T23:49:27.512459+00:00","updated_at":"2026-05-17T23:49:27.512459+00:00"}