{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:FOIHMNT2CPNBBHOXHU7SNDG7LF","short_pith_number":"pith:FOIHMNT2","schema_version":"1.0","canonical_sha256":"2b9076367a13da109dd73d3f268cdf594f087dc62b46111efe0ecbf36a00c2e7","source":{"kind":"arxiv","id":"1601.01974","version":2},"attestation_state":"computed","paper":{"title":"Scale-Free Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"D\\'avid P\\'al, Francesco Orabona","submitted_at":"2016-01-08T18:47:18Z","abstract_excerpt":"We design and analyze algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. Our algorithms are instances of the Follow the Regularized Leader (FTRL) and Mirror Descent (MD) meta-algorithms. We achieve adaptiveness to the norms of the loss vectors by scale invariance, i.e., our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. The algorithm based on FTRL works for any decision set, bounded or unbounded. For unbounded de"},"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":"1601.01974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-01-08T18:47:18Z","cross_cats_sorted":[],"title_canon_sha256":"e554b894a9041f51f4723107c5cedda7c3d8708bb7cd74f944f189f45e329342","abstract_canon_sha256":"1d9d3635c39349456b1f4620c5c22a5581cbca84906376eeff086c55d225101c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:55:04.178023Z","signature_b64":"0H58OFevU0S9uWjpYAkzK8DuEjsauMuYC1CkJVnGw88Wc4/HkliNBDPNm1SeH4jWpw2NGoYJ3P8Y+SPQ9lD5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b9076367a13da109dd73d3f268cdf594f087dc62b46111efe0ecbf36a00c2e7","last_reissued_at":"2026-05-18T00:55:04.177454Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:55:04.177454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scale-Free Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"D\\'avid P\\'al, Francesco Orabona","submitted_at":"2016-01-08T18:47:18Z","abstract_excerpt":"We design and analyze algorithms for online linear optimization that have optimal regret and at the same time do not need to know any upper or lower bounds on the norm of the loss vectors. Our algorithms are instances of the Follow the Regularized Leader (FTRL) and Mirror Descent (MD) meta-algorithms. We achieve adaptiveness to the norms of the loss vectors by scale invariance, i.e., our algorithms make exactly the same decisions if the sequence of loss vectors is multiplied by any positive constant. The algorithm based on FTRL works for any decision set, bounded or unbounded. For unbounded de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1601.01974","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":"1601.01974","created_at":"2026-05-18T00:55:04.177527+00:00"},{"alias_kind":"arxiv_version","alias_value":"1601.01974v2","created_at":"2026-05-18T00:55:04.177527+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1601.01974","created_at":"2026-05-18T00:55:04.177527+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOIHMNT2CPNB","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOIHMNT2CPNBBHOX","created_at":"2026-05-18T12:30:15.759754+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOIHMNT2","created_at":"2026-05-18T12:30:15.759754+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/FOIHMNT2CPNBBHOXHU7SNDG7LF","json":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF.json","graph_json":"https://pith.science/api/pith-number/FOIHMNT2CPNBBHOXHU7SNDG7LF/graph.json","events_json":"https://pith.science/api/pith-number/FOIHMNT2CPNBBHOXHU7SNDG7LF/events.json","paper":"https://pith.science/paper/FOIHMNT2"},"agent_actions":{"view_html":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF","download_json":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF.json","view_paper":"https://pith.science/paper/FOIHMNT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1601.01974&json=true","fetch_graph":"https://pith.science/api/pith-number/FOIHMNT2CPNBBHOXHU7SNDG7LF/graph.json","fetch_events":"https://pith.science/api/pith-number/FOIHMNT2CPNBBHOXHU7SNDG7LF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF/action/storage_attestation","attest_author":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF/action/author_attestation","sign_citation":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF/action/citation_signature","submit_replication":"https://pith.science/pith/FOIHMNT2CPNBBHOXHU7SNDG7LF/action/replication_record"}},"created_at":"2026-05-18T00:55:04.177527+00:00","updated_at":"2026-05-18T00:55:04.177527+00:00"}