{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EJFGS4SP6HEQUUWEVHMMIKEVMK","short_pith_number":"pith:EJFGS4SP","schema_version":"1.0","canonical_sha256":"224a69724ff1c90a52c4a9d8c4289562b5526fc8210971dd71933d90d97cd029","source":{"kind":"arxiv","id":"2409.11181","version":1},"attestation_state":"computed","paper":{"title":"Inexact Riemannian Gradient Descent Method for Nonconvex Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongxia Wang, Juan Zhou, Kangkang Deng, Zheng Peng","submitted_at":"2024-09-17T13:35:13Z","abstract_excerpt":"Gradient descent methods are fundamental first-order optimization algorithms in both Euclidean spaces and Riemannian manifolds. However, the exact gradient is not readily available in many scenarios. This paper proposes a novel inexact Riemannian gradient descent algorithm for nonconvex problems, accompanied by a convergence guarantee. In particular, we establish two inexact gradient conditions on Riemannian manifolds for the first time, enabling precise gradient approximations. Our method demonstrates strong convergence results for both gradient sequences and function values. The global conve"},"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":"2409.11181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"math.OC","submitted_at":"2024-09-17T13:35:13Z","cross_cats_sorted":[],"title_canon_sha256":"53077c9a48d40017dfa350685308788986c0b4e30f358801c4356b4d16d4520d","abstract_canon_sha256":"7462782f2a58504efaf7b99e44cb93b8eceb968ba88aa0ae5dcd5614c291a24a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:02.764994Z","signature_b64":"Oqjg+UEVO/TPyUAlEIzBlrJWVTk8gfuKvMPJ+Xp5rnUqt7BKzNrNprp4/+j8H05/zyfo5RvM0BC0+xwPlu9XCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"224a69724ff1c90a52c4a9d8c4289562b5526fc8210971dd71933d90d97cd029","last_reissued_at":"2026-07-05T09:08:02.764534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:02.764534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inexact Riemannian Gradient Descent Method for Nonconvex Optimization","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Hongxia Wang, Juan Zhou, Kangkang Deng, Zheng Peng","submitted_at":"2024-09-17T13:35:13Z","abstract_excerpt":"Gradient descent methods are fundamental first-order optimization algorithms in both Euclidean spaces and Riemannian manifolds. However, the exact gradient is not readily available in many scenarios. This paper proposes a novel inexact Riemannian gradient descent algorithm for nonconvex problems, accompanied by a convergence guarantee. In particular, we establish two inexact gradient conditions on Riemannian manifolds for the first time, enabling precise gradient approximations. Our method demonstrates strong convergence results for both gradient sequences and function values. The global conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11181","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/2409.11181/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":"2409.11181","created_at":"2026-07-05T09:08:02.764593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11181v1","created_at":"2026-07-05T09:08:02.764593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11181","created_at":"2026-07-05T09:08:02.764593+00:00"},{"alias_kind":"pith_short_12","alias_value":"EJFGS4SP6HEQ","created_at":"2026-07-05T09:08:02.764593+00:00"},{"alias_kind":"pith_short_16","alias_value":"EJFGS4SP6HEQUUWE","created_at":"2026-07-05T09:08:02.764593+00:00"},{"alias_kind":"pith_short_8","alias_value":"EJFGS4SP","created_at":"2026-07-05T09:08:02.764593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.04480","citing_title":"On the Wasserstein Geodesic Principal Component Analysis of probability measures","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK","json":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK.json","graph_json":"https://pith.science/api/pith-number/EJFGS4SP6HEQUUWEVHMMIKEVMK/graph.json","events_json":"https://pith.science/api/pith-number/EJFGS4SP6HEQUUWEVHMMIKEVMK/events.json","paper":"https://pith.science/paper/EJFGS4SP"},"agent_actions":{"view_html":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK","download_json":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK.json","view_paper":"https://pith.science/paper/EJFGS4SP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11181&json=true","fetch_graph":"https://pith.science/api/pith-number/EJFGS4SP6HEQUUWEVHMMIKEVMK/graph.json","fetch_events":"https://pith.science/api/pith-number/EJFGS4SP6HEQUUWEVHMMIKEVMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK/action/storage_attestation","attest_author":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK/action/author_attestation","sign_citation":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK/action/citation_signature","submit_replication":"https://pith.science/pith/EJFGS4SP6HEQUUWEVHMMIKEVMK/action/replication_record"}},"created_at":"2026-07-05T09:08:02.764593+00:00","updated_at":"2026-07-05T09:08:02.764593+00:00"}