{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7VAVY676UELM75L245BO6LSAHG","short_pith_number":"pith:7VAVY676","schema_version":"1.0","canonical_sha256":"fd415c7bfea116cff57ae742ef2e4039966610a6ef7ee4f2a3d37922a9d3b0e1","source":{"kind":"arxiv","id":"2206.05668","version":1},"attestation_state":"computed","paper":{"title":"Federated Learning on Riemannian Manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jiaxiang Li, Shiqian Ma","submitted_at":"2022-06-12T05:41:23Z","abstract_excerpt":"Federated learning (FL) has found many important applications in smart-phone-APP based machine learning applications. Although many algorithms have been studied for FL, to the best of our knowledge, algorithms for FL with nonconvex constraints have not been studied. This paper studies FL over Riemannian manifolds, which finds important applications such as federated PCA and federated kPCA. We propose a Riemannian federated SVRG (RFedSVRG) method to solve federated optimization over Riemannian manifolds. We analyze its convergence rate under different scenarios. Numerical experiments are conduc"},"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":"2206.05668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-12T05:41:23Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"37b33ff45bd3e0252b25bf34ea27e778ee463a5fc952e1d86d3022bb1bd49cba","abstract_canon_sha256":"64565fd0778fa19dd4e99264fdfd61ad7be4ea73fd39d0487d25e07175cf5367"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:01.728815Z","signature_b64":"sgz0rvrYPlSggTgH0aqoqyA+yI+ww0qzLoKolN7KbOhu6333RdvJzSkjVX1dSjrmSX0V5VZFe1xmdhERO/GLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd415c7bfea116cff57ae742ef2e4039966610a6ef7ee4f2a3d37922a9d3b0e1","last_reissued_at":"2026-07-05T04:31:01.728393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:01.728393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Learning on Riemannian Manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Jiaxiang Li, Shiqian Ma","submitted_at":"2022-06-12T05:41:23Z","abstract_excerpt":"Federated learning (FL) has found many important applications in smart-phone-APP based machine learning applications. Although many algorithms have been studied for FL, to the best of our knowledge, algorithms for FL with nonconvex constraints have not been studied. This paper studies FL over Riemannian manifolds, which finds important applications such as federated PCA and federated kPCA. We propose a Riemannian federated SVRG (RFedSVRG) method to solve federated optimization over Riemannian manifolds. We analyze its convergence rate under different scenarios. Numerical experiments are conduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.05668","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/2206.05668/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":"2206.05668","created_at":"2026-07-05T04:31:01.728450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.05668v1","created_at":"2026-07-05T04:31:01.728450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.05668","created_at":"2026-07-05T04:31:01.728450+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VAVY676UELM","created_at":"2026-07-05T04:31:01.728450+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VAVY676UELM75L2","created_at":"2026-07-05T04:31:01.728450+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VAVY676","created_at":"2026-07-05T04:31:01.728450+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11807","citing_title":"Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22494","citing_title":"FedSPDnet: Geometry-Aware Federated Deep Learning with SPDnet","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG","json":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG.json","graph_json":"https://pith.science/api/pith-number/7VAVY676UELM75L245BO6LSAHG/graph.json","events_json":"https://pith.science/api/pith-number/7VAVY676UELM75L245BO6LSAHG/events.json","paper":"https://pith.science/paper/7VAVY676"},"agent_actions":{"view_html":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG","download_json":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG.json","view_paper":"https://pith.science/paper/7VAVY676","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.05668&json=true","fetch_graph":"https://pith.science/api/pith-number/7VAVY676UELM75L245BO6LSAHG/graph.json","fetch_events":"https://pith.science/api/pith-number/7VAVY676UELM75L245BO6LSAHG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG/action/storage_attestation","attest_author":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG/action/author_attestation","sign_citation":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG/action/citation_signature","submit_replication":"https://pith.science/pith/7VAVY676UELM75L245BO6LSAHG/action/replication_record"}},"created_at":"2026-07-05T04:31:01.728450+00:00","updated_at":"2026-07-05T04:31:01.728450+00:00"}