{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:U55U5U4ATVO2RHARZ73AF2ZWJA","short_pith_number":"pith:U55U5U4A","schema_version":"1.0","canonical_sha256":"a77b4ed3809d5da89c11cff602eb36483782ddd2220334724b8a67e450cc1f1f","source":{"kind":"arxiv","id":"1403.0628","version":2},"attestation_state":"computed","paper":{"title":"Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Orabona, H. Brendan McMahan","submitted_at":"2014-03-03T23:06:24Z","abstract_excerpt":"We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving, several previous results as immediate corollaries. Moreover, using our tools, we develop an algorithm that provides a regret bound of $\\mathcal{O}\\Big(U \\sqrt{T \\log(U \\sqrt{T} \\log^2 T +1)}\\Big)$, where $U$ is the $L_2$ norm of an arbitrary comparator and both $T$ and $U$ are unknown to the player. This bound is optimal up to $\\sqrt{\\log \\log T}$ terms. When $T$ "},"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":"1403.0628","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-03-03T23:06:24Z","cross_cats_sorted":[],"title_canon_sha256":"b78d796f3f30fa0f3d623c51ba8a0167bff248fe4faf9cd126deedcb8e360b5f","abstract_canon_sha256":"681f965f1e018a90f9c8ea25e690a05a07ac078e2f56431ef6799517f196f030"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:24.016436Z","signature_b64":"oy3nK05AsaNg7jfDOjUGXMRMKhFpbYUO/Zzjl6+ctBbS1o4dk1cKqnMA+QL18oDk5lUA3MBidBPeGVgYSuQlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77b4ed3809d5da89c11cff602eb36483782ddd2220334724b8a67e450cc1f1f","last_reissued_at":"2026-05-18T02:51:24.015808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:24.015808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unconstrained Online Linear Learning in Hilbert Spaces: Minimax Algorithms and Normal Approximations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Francesco Orabona, H. Brendan McMahan","submitted_at":"2014-03-03T23:06:24Z","abstract_excerpt":"We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving, several previous results as immediate corollaries. Moreover, using our tools, we develop an algorithm that provides a regret bound of $\\mathcal{O}\\Big(U \\sqrt{T \\log(U \\sqrt{T} \\log^2 T +1)}\\Big)$, where $U$ is the $L_2$ norm of an arbitrary comparator and both $T$ and $U$ are unknown to the player. This bound is optimal up to $\\sqrt{\\log \\log T}$ terms. When $T$ "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1403.0628","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":"1403.0628","created_at":"2026-05-18T02:51:24.015911+00:00"},{"alias_kind":"arxiv_version","alias_value":"1403.0628v2","created_at":"2026-05-18T02:51:24.015911+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1403.0628","created_at":"2026-05-18T02:51:24.015911+00:00"},{"alias_kind":"pith_short_12","alias_value":"U55U5U4ATVO2","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_16","alias_value":"U55U5U4ATVO2RHAR","created_at":"2026-05-18T12:28:52.271510+00:00"},{"alias_kind":"pith_short_8","alias_value":"U55U5U4A","created_at":"2026-05-18T12:28:52.271510+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/U55U5U4ATVO2RHARZ73AF2ZWJA","json":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA.json","graph_json":"https://pith.science/api/pith-number/U55U5U4ATVO2RHARZ73AF2ZWJA/graph.json","events_json":"https://pith.science/api/pith-number/U55U5U4ATVO2RHARZ73AF2ZWJA/events.json","paper":"https://pith.science/paper/U55U5U4A"},"agent_actions":{"view_html":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA","download_json":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA.json","view_paper":"https://pith.science/paper/U55U5U4A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1403.0628&json=true","fetch_graph":"https://pith.science/api/pith-number/U55U5U4ATVO2RHARZ73AF2ZWJA/graph.json","fetch_events":"https://pith.science/api/pith-number/U55U5U4ATVO2RHARZ73AF2ZWJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA/action/storage_attestation","attest_author":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA/action/author_attestation","sign_citation":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA/action/citation_signature","submit_replication":"https://pith.science/pith/U55U5U4ATVO2RHARZ73AF2ZWJA/action/replication_record"}},"created_at":"2026-05-18T02:51:24.015911+00:00","updated_at":"2026-05-18T02:51:24.015911+00:00"}