{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:HULU6AXZ6MLKUUP6ORKRUKPZMT","short_pith_number":"pith:HULU6AXZ","schema_version":"1.0","canonical_sha256":"3d174f02f9f316aa51fe74551a29f964c8ac2ab7bac493b3783f69f9b765dc4c","source":{"kind":"arxiv","id":"1111.5280","version":4},"attestation_state":"computed","paper":{"title":"Stochastic gradient descent on Riemannian manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Silvere Bonnabel","submitted_at":"2011-11-22T18:41:12Z","abstract_excerpt":"Stochastic gradient descent is a simple approach to find the local minima of a cost function whose evaluations are corrupted by noise. In this paper, we develop a procedure extending stochastic gradient descent algorithms to the case where the function is defined on a Riemannian manifold. We prove that, as in the Euclidian case, the gradient descent algorithm converges to a critical point of the cost function. The algorithm has numerous potential applications, and is illustrated here by four examples. In particular a novel gossip algorithm on the set of covariance matrices is derived and teste"},"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":"1111.5280","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2011-11-22T18:41:12Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"19888cf26cd1fd92aabdcc8c5b61f68ad210a732983c795f9d6ac76693b30bc9","abstract_canon_sha256":"e89ae52c98675fd0eec665537835386a34a886bd82d033b07d32d4a1e61e3286"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:43.275083Z","signature_b64":"cszI6cAWtfiViEFpA8tEq2+IPWcTRDvoOF1zcfw//5jgdU/7N4SLefTmFYgspYl8eGe9/U2rzfGBXQIb49wTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d174f02f9f316aa51fe74551a29f964c8ac2ab7bac493b3783f69f9b765dc4c","last_reissued_at":"2026-05-18T00:58:43.274436Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:43.274436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic gradient descent on Riemannian manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Silvere Bonnabel","submitted_at":"2011-11-22T18:41:12Z","abstract_excerpt":"Stochastic gradient descent is a simple approach to find the local minima of a cost function whose evaluations are corrupted by noise. In this paper, we develop a procedure extending stochastic gradient descent algorithms to the case where the function is defined on a Riemannian manifold. We prove that, as in the Euclidian case, the gradient descent algorithm converges to a critical point of the cost function. The algorithm has numerous potential applications, and is illustrated here by four examples. In particular a novel gossip algorithm on the set of covariance matrices is derived and teste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1111.5280","kind":"arxiv","version":4},"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":"1111.5280","created_at":"2026-05-18T00:58:43.274538+00:00"},{"alias_kind":"arxiv_version","alias_value":"1111.5280v4","created_at":"2026-05-18T00:58:43.274538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1111.5280","created_at":"2026-05-18T00:58:43.274538+00:00"},{"alias_kind":"pith_short_12","alias_value":"HULU6AXZ6MLK","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_16","alias_value":"HULU6AXZ6MLKUUP6","created_at":"2026-05-18T12:26:30.835961+00:00"},{"alias_kind":"pith_short_8","alias_value":"HULU6AXZ","created_at":"2026-05-18T12:26:30.835961+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/HULU6AXZ6MLKUUP6ORKRUKPZMT","json":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT.json","graph_json":"https://pith.science/api/pith-number/HULU6AXZ6MLKUUP6ORKRUKPZMT/graph.json","events_json":"https://pith.science/api/pith-number/HULU6AXZ6MLKUUP6ORKRUKPZMT/events.json","paper":"https://pith.science/paper/HULU6AXZ"},"agent_actions":{"view_html":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT","download_json":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT.json","view_paper":"https://pith.science/paper/HULU6AXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1111.5280&json=true","fetch_graph":"https://pith.science/api/pith-number/HULU6AXZ6MLKUUP6ORKRUKPZMT/graph.json","fetch_events":"https://pith.science/api/pith-number/HULU6AXZ6MLKUUP6ORKRUKPZMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT/action/storage_attestation","attest_author":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT/action/author_attestation","sign_citation":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT/action/citation_signature","submit_replication":"https://pith.science/pith/HULU6AXZ6MLKUUP6ORKRUKPZMT/action/replication_record"}},"created_at":"2026-05-18T00:58:43.274538+00:00","updated_at":"2026-05-18T00:58:43.274538+00:00"}