{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ROAEHQ7DGCKTLDCRIK6YQFHZAO","short_pith_number":"pith:ROAEHQ7D","schema_version":"1.0","canonical_sha256":"8b8043c3e33095358c5142bd8814f90386f86b54e65440d34825fdec388b6c50","source":{"kind":"arxiv","id":"2410.05128","version":1},"attestation_state":"computed","paper":{"title":"Decentralized Online Riemannian Optimization with Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG"],"primary_cat":"math.OC","authors_text":"Hengchao Chen, Qiang Sun","submitted_at":"2024-10-07T15:28:34Z","abstract_excerpt":"This paper develops the first decentralized online Riemannian optimization algorithm on Hadamard manifolds. Our algorithm, the decentralized projected Riemannian gradient descent, iteratively performs local updates using projected Riemannian gradient descent and a consensus step via weighted Frechet mean. Theoretically, we establish linear variance reduction for the consensus step. Building on this, we prove a dynamic regret bound of order ${\\cal O}(\\sqrt{T(1+P_T)}/\\sqrt{(1-\\sigma_2(W))})$, where $T$ is the time horizon, $P_T$ represents the path variation measuring nonstationarity, and $\\sigm"},"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":"2410.05128","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-10-07T15:28:34Z","cross_cats_sorted":["math.DG"],"title_canon_sha256":"fb51589d67b1305ca8eb337a7df86bd3ff4e69a0e9669bf0a4a133898f066309","abstract_canon_sha256":"42ba670f62b7f37dc33966403429aaab67f7adfb5b86422e7b8d1eb6a4d7621a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:01.952833Z","signature_b64":"Bz7T1OwGAbnlAIDdy+w74kwG8H4qwuFYtFY1WaF/VFpEfGTO3qFKoBozrH3BWgYIDfLIjy7LP/HJBtujdttLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b8043c3e33095358c5142bd8814f90386f86b54e65440d34825fdec388b6c50","last_reissued_at":"2026-07-05T09:17:01.952349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:01.952349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decentralized Online Riemannian Optimization with Dynamic Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DG"],"primary_cat":"math.OC","authors_text":"Hengchao Chen, Qiang Sun","submitted_at":"2024-10-07T15:28:34Z","abstract_excerpt":"This paper develops the first decentralized online Riemannian optimization algorithm on Hadamard manifolds. Our algorithm, the decentralized projected Riemannian gradient descent, iteratively performs local updates using projected Riemannian gradient descent and a consensus step via weighted Frechet mean. Theoretically, we establish linear variance reduction for the consensus step. Building on this, we prove a dynamic regret bound of order ${\\cal O}(\\sqrt{T(1+P_T)}/\\sqrt{(1-\\sigma_2(W))})$, where $T$ is the time horizon, $P_T$ represents the path variation measuring nonstationarity, and $\\sigm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.05128","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/2410.05128/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":"2410.05128","created_at":"2026-07-05T09:17:01.952409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.05128v1","created_at":"2026-07-05T09:17:01.952409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.05128","created_at":"2026-07-05T09:17:01.952409+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROAEHQ7DGCKT","created_at":"2026-07-05T09:17:01.952409+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROAEHQ7DGCKTLDCR","created_at":"2026-07-05T09:17:01.952409+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROAEHQ7D","created_at":"2026-07-05T09:17:01.952409+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":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO","json":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO.json","graph_json":"https://pith.science/api/pith-number/ROAEHQ7DGCKTLDCRIK6YQFHZAO/graph.json","events_json":"https://pith.science/api/pith-number/ROAEHQ7DGCKTLDCRIK6YQFHZAO/events.json","paper":"https://pith.science/paper/ROAEHQ7D"},"agent_actions":{"view_html":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO","download_json":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO.json","view_paper":"https://pith.science/paper/ROAEHQ7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.05128&json=true","fetch_graph":"https://pith.science/api/pith-number/ROAEHQ7DGCKTLDCRIK6YQFHZAO/graph.json","fetch_events":"https://pith.science/api/pith-number/ROAEHQ7DGCKTLDCRIK6YQFHZAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO/action/storage_attestation","attest_author":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO/action/author_attestation","sign_citation":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO/action/citation_signature","submit_replication":"https://pith.science/pith/ROAEHQ7DGCKTLDCRIK6YQFHZAO/action/replication_record"}},"created_at":"2026-07-05T09:17:01.952409+00:00","updated_at":"2026-07-05T09:17:01.952409+00:00"}