{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ATOAATIKQ5T2HPUXOJSLC5GNTW","short_pith_number":"pith:ATOAATIK","schema_version":"1.0","canonical_sha256":"04dc004d0a8767a3be977264b174cd9db9796b257d48ebd1313b230475d118b1","source":{"kind":"arxiv","id":"1809.09350","version":3},"attestation_state":"computed","paper":{"title":"Fully Implicit Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaobing Song, Han Liu, Ji Liu, Tong Zhang, Yong Jiang","submitted_at":"2018-09-25T07:16:17Z","abstract_excerpt":"Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this paper we study a class of regularized online algorithms without linearizing the loss function or the regularizer, which we call \\emph{fully implicit online learning} (FIOL). We show that for arbitrary Bregman divergence, FIOL has the $O(\\sqrt{T})$ regret for general convex setting and $O(\\log T)$ regret for strongly convex setting, and the regret has an one"},"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":"1809.09350","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-25T07:16:17Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"df603fa616feb9a6e1017c507430c88a548fd5eb9643703732a4e0fb840c1f16","abstract_canon_sha256":"debf217bd1f1677380a8dc26911d93fc5c8b1773c7de950a42ead0685cdcdf36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:34.167508Z","signature_b64":"EtsJ6kjN9+bH0k84CfJQq3xjH6l3mfmxHLquPJHKCeLIuqYivrmKqdzWRVZVVVk9lRptrHsr5gl4qUAEEiyhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04dc004d0a8767a3be977264b174cd9db9796b257d48ebd1313b230475d118b1","last_reissued_at":"2026-05-17T23:54:34.166850Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:34.166850Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fully Implicit Online Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chaobing Song, Han Liu, Ji Liu, Tong Zhang, Yong Jiang","submitted_at":"2018-09-25T07:16:17Z","abstract_excerpt":"Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this paper we study a class of regularized online algorithms without linearizing the loss function or the regularizer, which we call \\emph{fully implicit online learning} (FIOL). We show that for arbitrary Bregman divergence, FIOL has the $O(\\sqrt{T})$ regret for general convex setting and $O(\\log T)$ regret for strongly convex setting, and the regret has an one"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.09350","kind":"arxiv","version":3},"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":"1809.09350","created_at":"2026-05-17T23:54:34.166951+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.09350v3","created_at":"2026-05-17T23:54:34.166951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.09350","created_at":"2026-05-17T23:54:34.166951+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATOAATIKQ5T2","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATOAATIKQ5T2HPUX","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATOAATIK","created_at":"2026-05-18T12:32:13.499390+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/ATOAATIKQ5T2HPUXOJSLC5GNTW","json":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW.json","graph_json":"https://pith.science/api/pith-number/ATOAATIKQ5T2HPUXOJSLC5GNTW/graph.json","events_json":"https://pith.science/api/pith-number/ATOAATIKQ5T2HPUXOJSLC5GNTW/events.json","paper":"https://pith.science/paper/ATOAATIK"},"agent_actions":{"view_html":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW","download_json":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW.json","view_paper":"https://pith.science/paper/ATOAATIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.09350&json=true","fetch_graph":"https://pith.science/api/pith-number/ATOAATIKQ5T2HPUXOJSLC5GNTW/graph.json","fetch_events":"https://pith.science/api/pith-number/ATOAATIKQ5T2HPUXOJSLC5GNTW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW/action/storage_attestation","attest_author":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW/action/author_attestation","sign_citation":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW/action/citation_signature","submit_replication":"https://pith.science/pith/ATOAATIKQ5T2HPUXOJSLC5GNTW/action/replication_record"}},"created_at":"2026-05-17T23:54:34.166951+00:00","updated_at":"2026-05-17T23:54:34.166951+00:00"}