{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YYEQ5OTWA4LRTTV2AKKS7E46XZ","short_pith_number":"pith:YYEQ5OTW","schema_version":"1.0","canonical_sha256":"c6090eba76071719ceba02952f939ebe4dbc54a9be2e97c1314082860f60ba5a","source":{"kind":"arxiv","id":"2309.14506","version":1},"attestation_state":"computed","paper":{"title":"Zeroth-order Riemannian Averaging Stochastic Approximation Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Jiaxiang Li, Krishnakumar Balasubramanian, Shiqian Ma","submitted_at":"2023-09-25T20:13:36Z","abstract_excerpt":"We present Zeroth-order Riemannian Averaging Stochastic Approximation (\\texttt{Zo-RASA}) algorithms for stochastic optimization on Riemannian manifolds. We show that \\texttt{Zo-RASA} achieves optimal sample complexities for generating $\\epsilon$-approximation first-order stationary solutions using only one-sample or constant-order batches in each iteration. Our approach employs Riemannian moving-average stochastic gradient estimators, and a novel Riemannian-Lyapunov analysis technique for convergence analysis. We improve the algorithm's practicality by using retractions and vector transport, i"},"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":"2309.14506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-09-25T20:13:36Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"23ec22cc39d74b04a634b47d1582930cfb13fd7aa2788f205d39847232d5ef2c","abstract_canon_sha256":"0d2a8882f9d593c5ed7df618d332c23c62aff8d00478e606d86f5ec09cd8e236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:55.342120Z","signature_b64":"L/pGAZl48lnlaEHglJa22AuoE8NNiqhfg5jpcEeKaUIenGpQWSMNornLyf1tkr3L+ecY9GlWz8Ok67S8LDs7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6090eba76071719ceba02952f939ebe4dbc54a9be2e97c1314082860f60ba5a","last_reissued_at":"2026-07-05T06:54:55.341701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:55.341701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zeroth-order Riemannian Averaging Stochastic Approximation Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Jiaxiang Li, Krishnakumar Balasubramanian, Shiqian Ma","submitted_at":"2023-09-25T20:13:36Z","abstract_excerpt":"We present Zeroth-order Riemannian Averaging Stochastic Approximation (\\texttt{Zo-RASA}) algorithms for stochastic optimization on Riemannian manifolds. We show that \\texttt{Zo-RASA} achieves optimal sample complexities for generating $\\epsilon$-approximation first-order stationary solutions using only one-sample or constant-order batches in each iteration. Our approach employs Riemannian moving-average stochastic gradient estimators, and a novel Riemannian-Lyapunov analysis technique for convergence analysis. We improve the algorithm's practicality by using retractions and vector transport, i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.14506","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/2309.14506/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":"2309.14506","created_at":"2026-07-05T06:54:55.341762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.14506v1","created_at":"2026-07-05T06:54:55.341762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.14506","created_at":"2026-07-05T06:54:55.341762+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYEQ5OTWA4LR","created_at":"2026-07-05T06:54:55.341762+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYEQ5OTWA4LRTTV2","created_at":"2026-07-05T06:54:55.341762+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYEQ5OTW","created_at":"2026-07-05T06:54:55.341762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.22855","citing_title":"Federated Learning on Riemannian Manifolds: A Gradient-Free Projection-Based Approach","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ","json":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ.json","graph_json":"https://pith.science/api/pith-number/YYEQ5OTWA4LRTTV2AKKS7E46XZ/graph.json","events_json":"https://pith.science/api/pith-number/YYEQ5OTWA4LRTTV2AKKS7E46XZ/events.json","paper":"https://pith.science/paper/YYEQ5OTW"},"agent_actions":{"view_html":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ","download_json":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ.json","view_paper":"https://pith.science/paper/YYEQ5OTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.14506&json=true","fetch_graph":"https://pith.science/api/pith-number/YYEQ5OTWA4LRTTV2AKKS7E46XZ/graph.json","fetch_events":"https://pith.science/api/pith-number/YYEQ5OTWA4LRTTV2AKKS7E46XZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ/action/storage_attestation","attest_author":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ/action/author_attestation","sign_citation":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ/action/citation_signature","submit_replication":"https://pith.science/pith/YYEQ5OTWA4LRTTV2AKKS7E46XZ/action/replication_record"}},"created_at":"2026-07-05T06:54:55.341762+00:00","updated_at":"2026-07-05T06:54:55.341762+00:00"}