{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LG252QW45FGA7634GTMJOBVJTN","short_pith_number":"pith:LG252QW4","schema_version":"1.0","canonical_sha256":"59b5dd42dce94c0ffb7c34d89706a99b5a3a150694b1dfa6601d1536755cb6cc","source":{"kind":"arxiv","id":"1702.03040","version":1},"attestation_state":"computed","paper":{"title":"Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Ruitong Huang, Tor Lattimore","submitted_at":"2017-02-10T01:59:02Z","abstract_excerpt":"The follow the leader (FTL) algorithm, perhaps the simplest of all online learning algorithms, is known to perform well when the loss functions it is used on are convex and positively curved. In this paper we ask whether there are other \"lucky\" settings when FTL achieves sublinear, \"small\" regret. In particular, we study the fundamental problem of linear prediction over a non-empty convex, compact domain. Amongst other results, we prove that the curvature of the boundary of the domain can act as if the losses were curved: In this case, we prove that as long as the mean of the loss vectors have"},"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":"1702.03040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-10T01:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"41460625584a623e06e98406f355d258c79d590d1c0766a62768d9f312e89ab2","abstract_canon_sha256":"d21d93b9d62f58d9768e51ec3fc73bcffe519aef7328fd68c2c83f669efa7dc1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:58.804131Z","signature_b64":"S3Mm6eLwcTfi8plDjPqCuLAOmoatUt8P86EAZeTPsnaxQVJmfrjRTgiYR6Rd3AyMi7sUKCH8LpPV/9gT0IaNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59b5dd42dce94c0ffb7c34d89706a99b5a3a150694b1dfa6601d1536755cb6cc","last_reissued_at":"2026-05-18T00:50:58.803573Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:58.803573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Following the Leader and Fast Rates in Linear Prediction: Curved Constraint Sets and Other Regularities","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andr\\'as Gy\\\"orgy, Csaba Szepesv\\'ari, Ruitong Huang, Tor Lattimore","submitted_at":"2017-02-10T01:59:02Z","abstract_excerpt":"The follow the leader (FTL) algorithm, perhaps the simplest of all online learning algorithms, is known to perform well when the loss functions it is used on are convex and positively curved. In this paper we ask whether there are other \"lucky\" settings when FTL achieves sublinear, \"small\" regret. In particular, we study the fundamental problem of linear prediction over a non-empty convex, compact domain. Amongst other results, we prove that the curvature of the boundary of the domain can act as if the losses were curved: In this case, we prove that as long as the mean of the loss vectors have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.03040","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":""},"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":"1702.03040","created_at":"2026-05-18T00:50:58.803641+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.03040v1","created_at":"2026-05-18T00:50:58.803641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.03040","created_at":"2026-05-18T00:50:58.803641+00:00"},{"alias_kind":"pith_short_12","alias_value":"LG252QW45FGA","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LG252QW45FGA7634","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LG252QW4","created_at":"2026-05-18T12:31:28.150371+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/LG252QW45FGA7634GTMJOBVJTN","json":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN.json","graph_json":"https://pith.science/api/pith-number/LG252QW45FGA7634GTMJOBVJTN/graph.json","events_json":"https://pith.science/api/pith-number/LG252QW45FGA7634GTMJOBVJTN/events.json","paper":"https://pith.science/paper/LG252QW4"},"agent_actions":{"view_html":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN","download_json":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN.json","view_paper":"https://pith.science/paper/LG252QW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.03040&json=true","fetch_graph":"https://pith.science/api/pith-number/LG252QW45FGA7634GTMJOBVJTN/graph.json","fetch_events":"https://pith.science/api/pith-number/LG252QW45FGA7634GTMJOBVJTN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN/action/storage_attestation","attest_author":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN/action/author_attestation","sign_citation":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN/action/citation_signature","submit_replication":"https://pith.science/pith/LG252QW45FGA7634GTMJOBVJTN/action/replication_record"}},"created_at":"2026-05-18T00:50:58.803641+00:00","updated_at":"2026-05-18T00:50:58.803641+00:00"}