{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WETYKEMRS4ZVROXDFNIOZXXCGM","short_pith_number":"pith:WETYKEMR","schema_version":"1.0","canonical_sha256":"b127851191973358bae32b50ecdee23339b3c0dd0123a9195c0f5551c309b070","source":{"kind":"arxiv","id":"2202.13603","version":2},"attestation_state":"computed","paper":{"title":"Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu","submitted_at":"2022-02-28T08:25:26Z","abstract_excerpt":"We study the problem of online generalized linear regression in the stochastic setting, where the label is generated from a generalized linear model with possibly unbounded additive noise. We provide a sharp analysis of the classical follow-the-regularized-leader (FTRL) algorithm to cope with the label noise. More specifically, for $\\sigma$-sub-Gaussian label noise, our analysis provides a regret upper bound of $O(\\sigma^2 d \\log T) + o(\\log T)$, where $d$ is the dimension of the input vector, $T$ is the total number of rounds. We also prove a $\\Omega(\\sigma^2d\\log(T/d))$ lower bound for stoch"},"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":"2202.13603","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-28T08:25:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"de91cb23eaf456ef79fc4c636ff48397961ace55118dcd5f83fbef04eb1717fc","abstract_canon_sha256":"3341cd171fbc1a3816afb00f351ba10bf70a74fd5a61f2732c653ddf5b01f4ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:53.917503Z","signature_b64":"Qo2xYwEZo/qO+WiWLbBYRdKmIEkPglcnqzwimBseiqhd3iL+1yDJSbG4so5IpXuh0xzujeF61XKTaiNnRD/JBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b127851191973358bae32b50ecdee23339b3c0dd0123a9195c0f5551c309b070","last_reissued_at":"2026-07-05T05:54:53.917087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:53.917087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Online Generalized Linear Regression with Stochastic Noise and Its Application to Heteroscedastic Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Heyang Zhao, Jiafan He, Quanquan Gu","submitted_at":"2022-02-28T08:25:26Z","abstract_excerpt":"We study the problem of online generalized linear regression in the stochastic setting, where the label is generated from a generalized linear model with possibly unbounded additive noise. We provide a sharp analysis of the classical follow-the-regularized-leader (FTRL) algorithm to cope with the label noise. More specifically, for $\\sigma$-sub-Gaussian label noise, our analysis provides a regret upper bound of $O(\\sigma^2 d \\log T) + o(\\log T)$, where $d$ is the dimension of the input vector, $T$ is the total number of rounds. We also prove a $\\Omega(\\sigma^2d\\log(T/d))$ lower bound for stoch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13603","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2202.13603/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":"2202.13603","created_at":"2026-07-05T05:54:53.917145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13603v2","created_at":"2026-07-05T05:54:53.917145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13603","created_at":"2026-07-05T05:54:53.917145+00:00"},{"alias_kind":"pith_short_12","alias_value":"WETYKEMRS4ZV","created_at":"2026-07-05T05:54:53.917145+00:00"},{"alias_kind":"pith_short_16","alias_value":"WETYKEMRS4ZVROXD","created_at":"2026-07-05T05:54:53.917145+00:00"},{"alias_kind":"pith_short_8","alias_value":"WETYKEMR","created_at":"2026-07-05T05:54:53.917145+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/WETYKEMRS4ZVROXDFNIOZXXCGM","json":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM.json","graph_json":"https://pith.science/api/pith-number/WETYKEMRS4ZVROXDFNIOZXXCGM/graph.json","events_json":"https://pith.science/api/pith-number/WETYKEMRS4ZVROXDFNIOZXXCGM/events.json","paper":"https://pith.science/paper/WETYKEMR"},"agent_actions":{"view_html":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM","download_json":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM.json","view_paper":"https://pith.science/paper/WETYKEMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13603&json=true","fetch_graph":"https://pith.science/api/pith-number/WETYKEMRS4ZVROXDFNIOZXXCGM/graph.json","fetch_events":"https://pith.science/api/pith-number/WETYKEMRS4ZVROXDFNIOZXXCGM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM/action/storage_attestation","attest_author":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM/action/author_attestation","sign_citation":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM/action/citation_signature","submit_replication":"https://pith.science/pith/WETYKEMRS4ZVROXDFNIOZXXCGM/action/replication_record"}},"created_at":"2026-07-05T05:54:53.917145+00:00","updated_at":"2026-07-05T05:54:53.917145+00:00"}