{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:P6TSDMXWVRZBBAT7PUC7PUWU25","short_pith_number":"pith:P6TSDMXW","schema_version":"1.0","canonical_sha256":"7fa721b2f6ac7210827f7d05f7d2d4d7760ab3850e5e9f59e681426218413110","source":{"kind":"arxiv","id":"1810.00760","version":2},"attestation_state":"computed","paper":{"title":"Riemannian Adaptive Optimization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea","submitted_at":"2018-10-01T15:31:36Z","abstract_excerpt":"Several first order stochastic optimization methods commonly used in the Euclidean domain such as stochastic gradient descent (SGD), accelerated gradient descent or variance reduced methods have already been adapted to certain Riemannian settings. However, some of the most popular of these optimization tools - namely Adam , Adagrad and the more recent Amsgrad - remain to be generalized to Riemannian manifolds. We discuss the difficulty of generalizing such adaptive schemes to the most agnostic Riemannian setting, and then provide algorithms and convergence proofs for geodesically convex object"},"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":"1810.00760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-01T15:31:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ba08e5f006aac7d6ff457fd52630c4bad0d6fe04872e84d0942ee32894d69bf5","abstract_canon_sha256":"d137538044fdaa3853ef0143c5e32e938b38e3a46675203a1610da3820fda541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:50.641567Z","signature_b64":"OmG6M0ixp7/DIQ3BeYCIrxHZaBTr8prbXCPto0/nXyfUOqn2DIjwwYeT8llmGT/oQLLGn+j3BM4wCH5uYAK3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fa721b2f6ac7210827f7d05f7d2d4d7760ab3850e5e9f59e681426218413110","last_reissued_at":"2026-05-17T23:53:50.640964Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:50.640964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Riemannian Adaptive Optimization Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gary B\\'ecigneul, Octavian-Eugen Ganea","submitted_at":"2018-10-01T15:31:36Z","abstract_excerpt":"Several first order stochastic optimization methods commonly used in the Euclidean domain such as stochastic gradient descent (SGD), accelerated gradient descent or variance reduced methods have already been adapted to certain Riemannian settings. However, some of the most popular of these optimization tools - namely Adam , Adagrad and the more recent Amsgrad - remain to be generalized to Riemannian manifolds. We discuss the difficulty of generalizing such adaptive schemes to the most agnostic Riemannian setting, and then provide algorithms and convergence proofs for geodesically convex object"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00760","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":""},"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":"1810.00760","created_at":"2026-05-17T23:53:50.641068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.00760v2","created_at":"2026-05-17T23:53:50.641068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00760","created_at":"2026-05-17T23:53:50.641068+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6TSDMXWVRZB","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6TSDMXWVRZBBAT7","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6TSDMXW","created_at":"2026-05-18T12:32:43.782077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.17779","citing_title":"Learning Variable-Length Tokenization for Generative Recommendation","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29057","citing_title":"LA-Sign: Looped Transformers with Geometry-aware Alignment for Skeleton-based Sign Language Recognition","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02969","citing_title":"Inversion-Free Natural Gradient Descent on Riemannian Manifolds","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12492","citing_title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25664","citing_title":"Deflation-Free Optimal Scoring","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24337","citing_title":"New non-Euclidean neural quantum states from additional types of hyperbolic recurrent neural networks","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25","json":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25.json","graph_json":"https://pith.science/api/pith-number/P6TSDMXWVRZBBAT7PUC7PUWU25/graph.json","events_json":"https://pith.science/api/pith-number/P6TSDMXWVRZBBAT7PUC7PUWU25/events.json","paper":"https://pith.science/paper/P6TSDMXW"},"agent_actions":{"view_html":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25","download_json":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25.json","view_paper":"https://pith.science/paper/P6TSDMXW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.00760&json=true","fetch_graph":"https://pith.science/api/pith-number/P6TSDMXWVRZBBAT7PUC7PUWU25/graph.json","fetch_events":"https://pith.science/api/pith-number/P6TSDMXWVRZBBAT7PUC7PUWU25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25/action/storage_attestation","attest_author":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25/action/author_attestation","sign_citation":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25/action/citation_signature","submit_replication":"https://pith.science/pith/P6TSDMXWVRZBBAT7PUC7PUWU25/action/replication_record"}},"created_at":"2026-05-17T23:53:50.641068+00:00","updated_at":"2026-05-17T23:53:50.641068+00:00"}