{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OR4PSOCQUZXXXROXIOYVRCVBPD","short_pith_number":"pith:OR4PSOCQ","schema_version":"1.0","canonical_sha256":"7478f93850a66f7bc5d743b1588aa178f4cfaba588025573766afe245e3e8b8c","source":{"kind":"arxiv","id":"2312.07990","version":1},"attestation_state":"computed","paper":{"title":"Convergence of Riemannian Stochastic Gradient Descent on Hadamard Manifold","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hideaki Iiduka, Hiroyuki Sakai","submitted_at":"2023-12-13T09:01:59Z","abstract_excerpt":"Novel convergence analyses are presented of Riemannian stochastic gradient descent (RSGD) on a Hadamard manifold. RSGD is the most basic Riemannian stochastic optimization algorithm and is used in many applications in the field of machine learning. The analyses incorporate the concept of mini-batch learning used in deep learning and overcome several problems in previous analyses. Four types of convergence analysis are described for both constant and decreasing step sizes. The number of steps needed for RSGD convergence is shown to be a convex monotone decreasing function of the batch size. App"},"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":"2312.07990","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-12-13T09:01:59Z","cross_cats_sorted":[],"title_canon_sha256":"6e328c403a8581eded8bec41141ec76122ad717e0e930bd21461dd6e07505fbf","abstract_canon_sha256":"9ccca79c525c9d1b1489ad699971d78f817f65adf79dcafb3f2efbd70308fffb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:23:51.071711Z","signature_b64":"uFHP/SOV4UXdeamiNLQ72mxFPIzaqkqby5/4k4EO6WHf3dJz5FFe7ZKA1Nh3gxlG3rT3kerHTMfnBD3Lx+pbCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7478f93850a66f7bc5d743b1588aa178f4cfaba588025573766afe245e3e8b8c","last_reissued_at":"2026-07-05T07:23:51.071145Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:23:51.071145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Riemannian Stochastic Gradient Descent on Hadamard Manifold","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hideaki Iiduka, Hiroyuki Sakai","submitted_at":"2023-12-13T09:01:59Z","abstract_excerpt":"Novel convergence analyses are presented of Riemannian stochastic gradient descent (RSGD) on a Hadamard manifold. RSGD is the most basic Riemannian stochastic optimization algorithm and is used in many applications in the field of machine learning. The analyses incorporate the concept of mini-batch learning used in deep learning and overcome several problems in previous analyses. Four types of convergence analysis are described for both constant and decreasing step sizes. The number of steps needed for RSGD convergence is shown to be a convex monotone decreasing function of the batch size. App"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07990","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/2312.07990/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":"2312.07990","created_at":"2026-07-05T07:23:51.071203+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07990v1","created_at":"2026-07-05T07:23:51.071203+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07990","created_at":"2026-07-05T07:23:51.071203+00:00"},{"alias_kind":"pith_short_12","alias_value":"OR4PSOCQUZXX","created_at":"2026-07-05T07:23:51.071203+00:00"},{"alias_kind":"pith_short_16","alias_value":"OR4PSOCQUZXXXROX","created_at":"2026-07-05T07:23:51.071203+00:00"},{"alias_kind":"pith_short_8","alias_value":"OR4PSOCQ","created_at":"2026-07-05T07:23:51.071203+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07779","citing_title":"Decentralized Online Riemannian Optimization Beyond Hadamard Manifolds","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD","json":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD.json","graph_json":"https://pith.science/api/pith-number/OR4PSOCQUZXXXROXIOYVRCVBPD/graph.json","events_json":"https://pith.science/api/pith-number/OR4PSOCQUZXXXROXIOYVRCVBPD/events.json","paper":"https://pith.science/paper/OR4PSOCQ"},"agent_actions":{"view_html":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD","download_json":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD.json","view_paper":"https://pith.science/paper/OR4PSOCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07990&json=true","fetch_graph":"https://pith.science/api/pith-number/OR4PSOCQUZXXXROXIOYVRCVBPD/graph.json","fetch_events":"https://pith.science/api/pith-number/OR4PSOCQUZXXXROXIOYVRCVBPD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD/action/storage_attestation","attest_author":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD/action/author_attestation","sign_citation":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD/action/citation_signature","submit_replication":"https://pith.science/pith/OR4PSOCQUZXXXROXIOYVRCVBPD/action/replication_record"}},"created_at":"2026-07-05T07:23:51.071203+00:00","updated_at":"2026-07-05T07:23:51.071203+00:00"}