{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NBAJ2PIZYYEG3LHTZH7L75AOMZ","short_pith_number":"pith:NBAJ2PIZ","schema_version":"1.0","canonical_sha256":"68409d3d19c6086dacf3c9febff40e66518aaa7e88cc89557f17ae1dbe0cd1df","source":{"kind":"arxiv","id":"1702.07870","version":1},"attestation_state":"computed","paper":{"title":"Online Learning with Many Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Shie Mannor","submitted_at":"2017-02-25T10:27:29Z","abstract_excerpt":"We study the problem of prediction with expert advice when the number of experts in question may be extremely large or even infinite. We devise an algorithm that obtains a tight regret bound of $\\widetilde{O}(\\epsilon T + N + \\sqrt{NT})$, where $N$ is the empirical $\\epsilon$-covering number of the sequence of loss functions generated by the environment. In addition, we present a hedging procedure that allows us to find the optimal $\\epsilon$ in hindsight.\n  Finally, we discuss a few interesting applications of our algorithm. We show how our algorithm is applicable in the approximately low ran"},"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":"1702.07870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-02-25T10:27:29Z","cross_cats_sorted":[],"title_canon_sha256":"7da8d78b188d393258ae30cdde4fbbac52f9b399dc8fd669803216652c96a9e8","abstract_canon_sha256":"dfd85d89110f50ef631bbced46dd677675cdee4a076f6fc5cbc56c45d23c6e82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:56.794746Z","signature_b64":"fZAoZwzggNO3aRYU/dkhgx5dLEr+KQ+Qso7es4ENwiIv6JbtSCHSpnEEmb3ULkgEZrEsR6E+CC/ycNehBL9kBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68409d3d19c6086dacf3c9febff40e66518aaa7e88cc89557f17ae1dbe0cd1df","last_reissued_at":"2026-05-18T00:49:56.794106Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:56.794106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning with Many Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alon Cohen, Shie Mannor","submitted_at":"2017-02-25T10:27:29Z","abstract_excerpt":"We study the problem of prediction with expert advice when the number of experts in question may be extremely large or even infinite. We devise an algorithm that obtains a tight regret bound of $\\widetilde{O}(\\epsilon T + N + \\sqrt{NT})$, where $N$ is the empirical $\\epsilon$-covering number of the sequence of loss functions generated by the environment. In addition, we present a hedging procedure that allows us to find the optimal $\\epsilon$ in hindsight.\n  Finally, we discuss a few interesting applications of our algorithm. We show how our algorithm is applicable in the approximately low ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.07870","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":"1702.07870","created_at":"2026-05-18T00:49:56.794214+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.07870v1","created_at":"2026-05-18T00:49:56.794214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.07870","created_at":"2026-05-18T00:49:56.794214+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBAJ2PIZYYEG","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBAJ2PIZYYEG3LHT","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBAJ2PIZ","created_at":"2026-05-18T12:31:31.346846+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/NBAJ2PIZYYEG3LHTZH7L75AOMZ","json":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ.json","graph_json":"https://pith.science/api/pith-number/NBAJ2PIZYYEG3LHTZH7L75AOMZ/graph.json","events_json":"https://pith.science/api/pith-number/NBAJ2PIZYYEG3LHTZH7L75AOMZ/events.json","paper":"https://pith.science/paper/NBAJ2PIZ"},"agent_actions":{"view_html":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ","download_json":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ.json","view_paper":"https://pith.science/paper/NBAJ2PIZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.07870&json=true","fetch_graph":"https://pith.science/api/pith-number/NBAJ2PIZYYEG3LHTZH7L75AOMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/NBAJ2PIZYYEG3LHTZH7L75AOMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ/action/storage_attestation","attest_author":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ/action/author_attestation","sign_citation":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ/action/citation_signature","submit_replication":"https://pith.science/pith/NBAJ2PIZYYEG3LHTZH7L75AOMZ/action/replication_record"}},"created_at":"2026-05-18T00:49:56.794214+00:00","updated_at":"2026-05-18T00:49:56.794214+00:00"}