{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JWVRD3L4ZXFB2CG76Q5N3Y44DD","short_pith_number":"pith:JWVRD3L4","schema_version":"1.0","canonical_sha256":"4dab11ed7ccdca1d08dff43adde39c18da27f4aefdebea3d51b8df57dcf5a8ad","source":{"kind":"arxiv","id":"2603.17527","version":2},"attestation_state":"computed","paper":{"title":"Mirror Descent on Riemannian Manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Jiaxin Jiang, Jiyuan Tan, Lei Shi","submitted_at":"2026-03-18T09:31:39Z","abstract_excerpt":"Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network training. This paper generalizes MD to optimization on Riemannian manifolds. In particular, we develop a Riemannian Mirror Descent (RMD) framework via reparameterization and further propose a stochastic variant of RMD. We also establish non-asymptotic convergence guarantees for both RMD and stochastic RMD. As an application to the Stiefel manifold, our RMD framework reduces to the Curvilinear Gradient Descent (CGD) method p"},"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":"2603.17527","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-03-18T09:31:39Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"a1ad19926979895747f70f30d7310d46b8c5cd6b4f6a5c0d72a1552b975c9e65","abstract_canon_sha256":"e41a2b2d66f4a1dce6f0cfc230326a61a129ce1e241438e8d3eb2c48f8b06925"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:25.121308Z","signature_b64":"ueJxZCTHz8WxC3umv1e1a6K5sRYKtUWX3wXqehZ77pH4G/fXAJTmU6z42H7UyOTQdwSBhGuPS6C9NNogtR3ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dab11ed7ccdca1d08dff43adde39c18da27f4aefdebea3d51b8df57dcf5a8ad","last_reissued_at":"2026-06-12T01:09:25.120838Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:25.120838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirror Descent on Riemannian Manifolds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"Jiaxin Jiang, Jiyuan Tan, Lei Shi","submitted_at":"2026-03-18T09:31:39Z","abstract_excerpt":"Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network training. This paper generalizes MD to optimization on Riemannian manifolds. In particular, we develop a Riemannian Mirror Descent (RMD) framework via reparameterization and further propose a stochastic variant of RMD. We also establish non-asymptotic convergence guarantees for both RMD and stochastic RMD. As an application to the Stiefel manifold, our RMD framework reduces to the Curvilinear Gradient Descent (CGD) method p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.17527","kind":"arxiv","version":2},"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/2603.17527/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":"2603.17527","created_at":"2026-06-12T01:09:25.120889+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.17527v2","created_at":"2026-06-12T01:09:25.120889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.17527","created_at":"2026-06-12T01:09:25.120889+00:00"},{"alias_kind":"pith_short_12","alias_value":"JWVRD3L4ZXFB","created_at":"2026-06-12T01:09:25.120889+00:00"},{"alias_kind":"pith_short_16","alias_value":"JWVRD3L4ZXFB2CG7","created_at":"2026-06-12T01:09:25.120889+00:00"},{"alias_kind":"pith_short_8","alias_value":"JWVRD3L4","created_at":"2026-06-12T01:09:25.120889+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/JWVRD3L4ZXFB2CG76Q5N3Y44DD","json":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD.json","graph_json":"https://pith.science/api/pith-number/JWVRD3L4ZXFB2CG76Q5N3Y44DD/graph.json","events_json":"https://pith.science/api/pith-number/JWVRD3L4ZXFB2CG76Q5N3Y44DD/events.json","paper":"https://pith.science/paper/JWVRD3L4"},"agent_actions":{"view_html":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD","download_json":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD.json","view_paper":"https://pith.science/paper/JWVRD3L4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.17527&json=true","fetch_graph":"https://pith.science/api/pith-number/JWVRD3L4ZXFB2CG76Q5N3Y44DD/graph.json","fetch_events":"https://pith.science/api/pith-number/JWVRD3L4ZXFB2CG76Q5N3Y44DD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD/action/storage_attestation","attest_author":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD/action/author_attestation","sign_citation":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD/action/citation_signature","submit_replication":"https://pith.science/pith/JWVRD3L4ZXFB2CG76Q5N3Y44DD/action/replication_record"}},"created_at":"2026-06-12T01:09:25.120889+00:00","updated_at":"2026-06-12T01:09:25.120889+00:00"}