{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RAWMIIDN6EZ2LLZO4J4D2UKLFG","short_pith_number":"pith:RAWMIIDN","schema_version":"1.0","canonical_sha256":"882cc4206df133a5af2ee2783d514b29b867e4d3e30545dcc2d8edf6dd9aa107","source":{"kind":"arxiv","id":"2111.11550","version":1},"attestation_state":"computed","paper":{"title":"Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dheeraj Baby, Hilaf Hasson, Yuyang Wang","submitted_at":"2021-11-22T21:52:47Z","abstract_excerpt":"We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation $V_T$ of the comparator sequence. Specifically, we show that SA algorithms enjoy $\\tilde O(\\sqrt{TV_T} \\vee \\log T)$ and $\\tilde O(\\sqrt{dTV_T} \\vee d\\log T)$ dynamic regret for strongly convex and exp-concave losses respectiv"},"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":"2111.11550","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T21:52:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd65d3f7a46b71150ef455000c07fd6b72e345bec9faa7f65d48924bf5a35c53","abstract_canon_sha256":"5ddc9873d030017a16549cf9b1b893faa591e07505bdf7f5890d931a28311ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:34:10.352533Z","signature_b64":"s8WulQKVHFezVcSn2733vLCzCGodZTM9rbjdcB+1mbD562GqAhUiOYmzgp3Ch2y2OLGiYfV4gE0x3yKPkVfuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"882cc4206df133a5af2ee2783d514b29b867e4d3e30545dcc2d8edf6dd9aa107","last_reissued_at":"2026-07-05T03:34:10.352048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:34:10.352048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Regret for Strongly Adaptive Methods and Optimality of Online KRR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dheeraj Baby, Hilaf Hasson, Yuyang Wang","submitted_at":"2021-11-22T21:52:47Z","abstract_excerpt":"We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation $V_T$ of the comparator sequence. Specifically, we show that SA algorithms enjoy $\\tilde O(\\sqrt{TV_T} \\vee \\log T)$ and $\\tilde O(\\sqrt{dTV_T} \\vee d\\log T)$ dynamic regret for strongly convex and exp-concave losses respectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11550","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2111.11550/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":"2111.11550","created_at":"2026-07-05T03:34:10.352105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11550v1","created_at":"2026-07-05T03:34:10.352105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11550","created_at":"2026-07-05T03:34:10.352105+00:00"},{"alias_kind":"pith_short_12","alias_value":"RAWMIIDN6EZ2","created_at":"2026-07-05T03:34:10.352105+00:00"},{"alias_kind":"pith_short_16","alias_value":"RAWMIIDN6EZ2LLZO","created_at":"2026-07-05T03:34:10.352105+00:00"},{"alias_kind":"pith_short_8","alias_value":"RAWMIIDN","created_at":"2026-07-05T03:34:10.352105+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.25021","citing_title":"Dynamic Regret for Online Regression in RKHS via Discounted VAW and Subspace Approximation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG","json":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG.json","graph_json":"https://pith.science/api/pith-number/RAWMIIDN6EZ2LLZO4J4D2UKLFG/graph.json","events_json":"https://pith.science/api/pith-number/RAWMIIDN6EZ2LLZO4J4D2UKLFG/events.json","paper":"https://pith.science/paper/RAWMIIDN"},"agent_actions":{"view_html":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG","download_json":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG.json","view_paper":"https://pith.science/paper/RAWMIIDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11550&json=true","fetch_graph":"https://pith.science/api/pith-number/RAWMIIDN6EZ2LLZO4J4D2UKLFG/graph.json","fetch_events":"https://pith.science/api/pith-number/RAWMIIDN6EZ2LLZO4J4D2UKLFG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG/action/storage_attestation","attest_author":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG/action/author_attestation","sign_citation":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG/action/citation_signature","submit_replication":"https://pith.science/pith/RAWMIIDN6EZ2LLZO4J4D2UKLFG/action/replication_record"}},"created_at":"2026-07-05T03:34:10.352105+00:00","updated_at":"2026-07-05T03:34:10.352105+00:00"}