{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CVNTDA7CO77474TZ544AGFE7P3","short_pith_number":"pith:CVNTDA7C","schema_version":"1.0","canonical_sha256":"155b3183e277ffcff279ef3803149f7eccdd917528a33fd5c8270c4bb596c477","source":{"kind":"arxiv","id":"2104.13790","version":3},"attestation_state":"computed","paper":{"title":"FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Hussain, Cheng cheng, Kaizhu Huang, Xin Liu, Xuguang Wang, Yangfan Zhou","submitted_at":"2021-04-28T14:23:37Z","abstract_excerpt":"AdaBelief, one of the current best optimizers, demonstrates superior generalization ability compared to the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in that it has a data-dependent $O(\\sqrt{T})$ regret bound when objective functions are convex, where $T$ is a time horizon. It remains however an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. %on how to exploit strong convexity to further improve the convergence rate of AdaBelief. To this end, we "},"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":"2104.13790","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-04-28T14:23:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"de947cb037d86a2daa359363a43b11403f7afa12585be09254718ca528926faa","abstract_canon_sha256":"79c1afe9f89ebdc4ee46a37d651f3bc5a0695b68461dd93ede440dfc200806e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:19.138752Z","signature_b64":"5gR+GdSqwGhkukKp3UqNXF8j5B0kcV6tUYGIk87T0EpfcLRW9pmhj7KnCF7GRVL61T8myXk6TQ77VPRy1sUaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"155b3183e277ffcff279ef3803149f7eccdd917528a33fd5c8270c4bb596c477","last_reissued_at":"2026-07-05T04:26:19.138324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:19.138324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastAdaBelief: Improving Convergence Rate for Belief-based Adaptive Optimizers by Exploiting Strong Convexity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Hussain, Cheng cheng, Kaizhu Huang, Xin Liu, Xuguang Wang, Yangfan Zhou","submitted_at":"2021-04-28T14:23:37Z","abstract_excerpt":"AdaBelief, one of the current best optimizers, demonstrates superior generalization ability compared to the popular Adam algorithm by viewing the exponential moving average of observed gradients. AdaBelief is theoretically appealing in that it has a data-dependent $O(\\sqrt{T})$ regret bound when objective functions are convex, where $T$ is a time horizon. It remains however an open problem whether the convergence rate can be further improved without sacrificing its generalization ability. %on how to exploit strong convexity to further improve the convergence rate of AdaBelief. To this end, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.13790","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.13790/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":"2104.13790","created_at":"2026-07-05T04:26:19.138378+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.13790v3","created_at":"2026-07-05T04:26:19.138378+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.13790","created_at":"2026-07-05T04:26:19.138378+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVNTDA7CO774","created_at":"2026-07-05T04:26:19.138378+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVNTDA7CO77474TZ","created_at":"2026-07-05T04:26:19.138378+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVNTDA7C","created_at":"2026-07-05T04:26:19.138378+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/CVNTDA7CO77474TZ544AGFE7P3","json":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3.json","graph_json":"https://pith.science/api/pith-number/CVNTDA7CO77474TZ544AGFE7P3/graph.json","events_json":"https://pith.science/api/pith-number/CVNTDA7CO77474TZ544AGFE7P3/events.json","paper":"https://pith.science/paper/CVNTDA7C"},"agent_actions":{"view_html":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3","download_json":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3.json","view_paper":"https://pith.science/paper/CVNTDA7C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.13790&json=true","fetch_graph":"https://pith.science/api/pith-number/CVNTDA7CO77474TZ544AGFE7P3/graph.json","fetch_events":"https://pith.science/api/pith-number/CVNTDA7CO77474TZ544AGFE7P3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3/action/storage_attestation","attest_author":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3/action/author_attestation","sign_citation":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3/action/citation_signature","submit_replication":"https://pith.science/pith/CVNTDA7CO77474TZ544AGFE7P3/action/replication_record"}},"created_at":"2026-07-05T04:26:19.138378+00:00","updated_at":"2026-07-05T04:26:19.138378+00:00"}