{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4AJHTG3SHAD4U4ULMRK2QJRKB2","short_pith_number":"pith:4AJHTG3S","schema_version":"1.0","canonical_sha256":"e012799b723807ca728b6455a8262a0e8eeb2176c1e92581b9f8c85b90a035d8","source":{"kind":"arxiv","id":"2410.17336","version":1},"attestation_state":"computed","paper":{"title":"Computing Optimal Regularizers for Online Linear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jon Schneider, Khashayar Gatmiry, Stefanie Jegelka","submitted_at":"2024-10-22T18:10:50Z","abstract_excerpt":"Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent factors in the regret bound. We present an algorithm that takes as input convex and symmetric action sets and loss sets for a specific OLO instance, and outputs a regularizer such that running FTRL with this regularizer guarantees regret within a universal constant factor of the best possible regret bound. In particular, for any choice of (convex, symmetric) ac"},"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":"2410.17336","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-22T18:10:50Z","cross_cats_sorted":["cs.DS","cs.GT","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"ac844d73f204698423f3928d2557e94b4f4009f4f1b6e3410de30388f1178890","abstract_canon_sha256":"469f3e9a0d798f38cca7e3b045bd49ad925c48c92891efdd16ee284b832be385"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:20.548920Z","signature_b64":"6272JG6gEFNxyCFIYCCm6RY3dhRNGsvj8JkXTekQ6hJqK7c/RdCe6G2JxFlc0kT5+Oxc9pACmL66N6XOTzLwCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e012799b723807ca728b6455a8262a0e8eeb2176c1e92581b9f8c85b90a035d8","last_reissued_at":"2026-07-05T09:24:20.548417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:20.548417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Computing Optimal Regularizers for Online Linear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.GT","math.ST","stat.ML","stat.TH"],"primary_cat":"cs.LG","authors_text":"Jon Schneider, Khashayar Gatmiry, Stefanie Jegelka","submitted_at":"2024-10-22T18:10:50Z","abstract_excerpt":"Follow-the-Regularized-Leader (FTRL) algorithms are a popular class of learning algorithms for online linear optimization (OLO) that guarantee sub-linear regret, but the choice of regularizer can significantly impact dimension-dependent factors in the regret bound. We present an algorithm that takes as input convex and symmetric action sets and loss sets for a specific OLO instance, and outputs a regularizer such that running FTRL with this regularizer guarantees regret within a universal constant factor of the best possible regret bound. In particular, for any choice of (convex, symmetric) ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17336","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/2410.17336/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":"2410.17336","created_at":"2026-07-05T09:24:20.548472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.17336v1","created_at":"2026-07-05T09:24:20.548472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17336","created_at":"2026-07-05T09:24:20.548472+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AJHTG3SHAD4","created_at":"2026-07-05T09:24:20.548472+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AJHTG3SHAD4U4UL","created_at":"2026-07-05T09:24:20.548472+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AJHTG3S","created_at":"2026-07-05T09:24:20.548472+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.21460","citing_title":"High-Dimensional Calibration from Swap Regret","ref_index":2017,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2","json":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2.json","graph_json":"https://pith.science/api/pith-number/4AJHTG3SHAD4U4ULMRK2QJRKB2/graph.json","events_json":"https://pith.science/api/pith-number/4AJHTG3SHAD4U4ULMRK2QJRKB2/events.json","paper":"https://pith.science/paper/4AJHTG3S"},"agent_actions":{"view_html":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2","download_json":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2.json","view_paper":"https://pith.science/paper/4AJHTG3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.17336&json=true","fetch_graph":"https://pith.science/api/pith-number/4AJHTG3SHAD4U4ULMRK2QJRKB2/graph.json","fetch_events":"https://pith.science/api/pith-number/4AJHTG3SHAD4U4ULMRK2QJRKB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2/action/storage_attestation","attest_author":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2/action/author_attestation","sign_citation":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2/action/citation_signature","submit_replication":"https://pith.science/pith/4AJHTG3SHAD4U4ULMRK2QJRKB2/action/replication_record"}},"created_at":"2026-07-05T09:24:20.548472+00:00","updated_at":"2026-07-05T09:24:20.548472+00:00"}