{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NSLWLRT3B6HGU3L5J677YH6KJ2","short_pith_number":"pith:NSLWLRT3","schema_version":"1.0","canonical_sha256":"6c9765c67b0f8e6a6d7d4fbffc1fca4e8eaea6be44979f033591d076e82703bc","source":{"kind":"arxiv","id":"2406.00655","version":1},"attestation_state":"computed","paper":{"title":"Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IT","math.IT","q-fin.PM"],"primary_cat":"cs.LG","authors_text":"Andrzej Cichocki, Auxiliadora Sarmiento, Sergio Cruces, Toshihisa Tanaka","submitted_at":"2024-06-02T07:56:30Z","abstract_excerpt":"This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function. Collectively referred to as EGAB, the proposed updates belong to the category of multiplicative gradient algorithms for positive data and demonstrate considerable flexibility by controlling iteration behavior and performance through three hyperparameters: $\\alpha$, $\\beta$, and the learning rate $\\eta$. To enforce a unit $l_1$ norm constraint for nonnegative weight vectors within generalized EGAB algorithms, we develop two slightly distinct appr"},"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":"2406.00655","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-02T07:56:30Z","cross_cats_sorted":["cs.IT","math.IT","q-fin.PM"],"title_canon_sha256":"d6c1709d674754879cb80232cf39e62605deecb964f81795e1c467fc68976c74","abstract_canon_sha256":"dbc23fb42afb1174ee7cc1098e42ddd09780d3db53c8adc50143b87c58827731"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:02.215225Z","signature_b64":"17sC+cA+ZTFP4w+tZ8rg06RsLkIxxQVh8RFOH/kiK4KyDFPCqUo2GY2k3IW8IRGy8xtewXpoaGHRu6CTdcISDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c9765c67b0f8e6a6d7d4fbffc1fca4e8eaea6be44979f033591d076e82703bc","last_reissued_at":"2026-07-05T09:54:02.214839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:02.214839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IT","math.IT","q-fin.PM"],"primary_cat":"cs.LG","authors_text":"Andrzej Cichocki, Auxiliadora Sarmiento, Sergio Cruces, Toshihisa Tanaka","submitted_at":"2024-06-02T07:56:30Z","abstract_excerpt":"This paper introduces a novel family of generalized exponentiated gradient (EG) updates derived from an Alpha-Beta divergence regularization function. Collectively referred to as EGAB, the proposed updates belong to the category of multiplicative gradient algorithms for positive data and demonstrate considerable flexibility by controlling iteration behavior and performance through three hyperparameters: $\\alpha$, $\\beta$, and the learning rate $\\eta$. To enforce a unit $l_1$ norm constraint for nonnegative weight vectors within generalized EGAB algorithms, we develop two slightly distinct appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00655","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/2406.00655/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":"2406.00655","created_at":"2026-07-05T09:54:02.214891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.00655v1","created_at":"2026-07-05T09:54:02.214891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00655","created_at":"2026-07-05T09:54:02.214891+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSLWLRT3B6HG","created_at":"2026-07-05T09:54:02.214891+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSLWLRT3B6HGU3L5","created_at":"2026-07-05T09:54:02.214891+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSLWLRT3","created_at":"2026-07-05T09:54:02.214891+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/NSLWLRT3B6HGU3L5J677YH6KJ2","json":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2.json","graph_json":"https://pith.science/api/pith-number/NSLWLRT3B6HGU3L5J677YH6KJ2/graph.json","events_json":"https://pith.science/api/pith-number/NSLWLRT3B6HGU3L5J677YH6KJ2/events.json","paper":"https://pith.science/paper/NSLWLRT3"},"agent_actions":{"view_html":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2","download_json":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2.json","view_paper":"https://pith.science/paper/NSLWLRT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.00655&json=true","fetch_graph":"https://pith.science/api/pith-number/NSLWLRT3B6HGU3L5J677YH6KJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/NSLWLRT3B6HGU3L5J677YH6KJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2/action/storage_attestation","attest_author":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2/action/author_attestation","sign_citation":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2/action/citation_signature","submit_replication":"https://pith.science/pith/NSLWLRT3B6HGU3L5J677YH6KJ2/action/replication_record"}},"created_at":"2026-07-05T09:54:02.214891+00:00","updated_at":"2026-07-05T09:54:02.214891+00:00"}