{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XGZ3CW7F267PCFSOKLKW5QO6HW","short_pith_number":"pith:XGZ3CW7F","schema_version":"1.0","canonical_sha256":"b9b3b15be5d7bef1164e52d56ec1de3d86b4c29918df7524ff6c9e9d1930c69e","source":{"kind":"arxiv","id":"2309.08339","version":3},"attestation_state":"computed","paper":{"title":"A Theoretical and Empirical Study on the Convergence of Adam with an \"Exact\" Constant Step Size in Non-Convex Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Alokendu Mazumder, Bhartendu Kumar, Manan Tayal, Punit Rathore, Rishabh Sabharwal","submitted_at":"2023-09-15T11:47:14Z","abstract_excerpt":"In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally, questions about their theoretical convergence properties continue to be a subject of interest. In this paper, we theoretically analyse a constant step size version of Adam in the non-convex setting and discuss why it is important for the convergence of Adam to use a fixed step size. This work demonstrates the derivation and effective implementation of a cons"},"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":"2309.08339","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-15T11:47:14Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"4d0f447fbcbaa3bc45cc4164423e6280956372b385a70b8b61e61f8a9bf6d10c","abstract_canon_sha256":"ecd2366ae19670598da469416d3a9628e198787746779443c65aa4966f0dd1f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:14.490475Z","signature_b64":"bu/k7CFJmNWJBP2aEg4YjnIjyVy9V1dx8JbNohA8ViL1lVpV8tBjjGnnTPuE/h/RUO5z0n/L/SVtvX2n0ptADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9b3b15be5d7bef1164e52d56ec1de3d86b4c29918df7524ff6c9e9d1930c69e","last_reissued_at":"2026-07-05T08:04:14.490038Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:14.490038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theoretical and Empirical Study on the Convergence of Adam with an \"Exact\" Constant Step Size in Non-Convex Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Alokendu Mazumder, Bhartendu Kumar, Manan Tayal, Punit Rathore, Rishabh Sabharwal","submitted_at":"2023-09-15T11:47:14Z","abstract_excerpt":"In neural network training, RMSProp and Adam remain widely favoured optimisation algorithms. One of the keys to their performance lies in selecting the correct step size, which can significantly influence their effectiveness. Additionally, questions about their theoretical convergence properties continue to be a subject of interest. In this paper, we theoretically analyse a constant step size version of Adam in the non-convex setting and discuss why it is important for the convergence of Adam to use a fixed step size. This work demonstrates the derivation and effective implementation of a cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.08339","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/2309.08339/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":"2309.08339","created_at":"2026-07-05T08:04:14.490097+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.08339v3","created_at":"2026-07-05T08:04:14.490097+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.08339","created_at":"2026-07-05T08:04:14.490097+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGZ3CW7F267P","created_at":"2026-07-05T08:04:14.490097+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGZ3CW7F267PCFSO","created_at":"2026-07-05T08:04:14.490097+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGZ3CW7F","created_at":"2026-07-05T08:04:14.490097+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/XGZ3CW7F267PCFSOKLKW5QO6HW","json":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW.json","graph_json":"https://pith.science/api/pith-number/XGZ3CW7F267PCFSOKLKW5QO6HW/graph.json","events_json":"https://pith.science/api/pith-number/XGZ3CW7F267PCFSOKLKW5QO6HW/events.json","paper":"https://pith.science/paper/XGZ3CW7F"},"agent_actions":{"view_html":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW","download_json":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW.json","view_paper":"https://pith.science/paper/XGZ3CW7F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.08339&json=true","fetch_graph":"https://pith.science/api/pith-number/XGZ3CW7F267PCFSOKLKW5QO6HW/graph.json","fetch_events":"https://pith.science/api/pith-number/XGZ3CW7F267PCFSOKLKW5QO6HW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW/action/storage_attestation","attest_author":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW/action/author_attestation","sign_citation":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW/action/citation_signature","submit_replication":"https://pith.science/pith/XGZ3CW7F267PCFSOKLKW5QO6HW/action/replication_record"}},"created_at":"2026-07-05T08:04:14.490097+00:00","updated_at":"2026-07-05T08:04:14.490097+00:00"}