{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:65F6HPC65ZE3RJKGFCWPUTOJJK","short_pith_number":"pith:65F6HPC6","schema_version":"1.0","canonical_sha256":"f74be3bc5eee49b8a54628acfa4dc94ab26cfe3444419d7afd2e184b74f20342","source":{"kind":"arxiv","id":"2203.01757","version":3},"attestation_state":"computed","paper":{"title":"Complexity and performance for two classes of noise-tolerant first-order algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ph. L. Toint, S. Gratton, S. Jerad","submitted_at":"2022-03-03T15:10:40Z","abstract_excerpt":"Two classes of algorithms for optimization in the presence of noise are presented, that do not require the evaluation of the objective function. The first generalizes the well-known Adagrad method. Its complexity is then analyzed as a function of its parameters. A second class of algorithms is then derived whose complexity is at least as good as that of the first class. Initial numerical experiments on finite-sum problems arising from deep-learning applications suggest that methods of the second class may outperform those of the first."},"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":"2203.01757","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-03-03T15:10:40Z","cross_cats_sorted":[],"title_canon_sha256":"efce2d601317000a771e51671571138d4a03c4db8a2950b3c8583cf1819cc21a","abstract_canon_sha256":"0eedf0149c6d49f833fdff2210a878061756aa4d998f59ee469c34e2d297095e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:35.858118Z","signature_b64":"T39va0tGTlbWmz8pTyC8eXdr/0Z0ozpjWmwT5NbtfbRT/vARjb0kyXGHlbLruBPCIC4E43UL8wj3xIT5i5xZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74be3bc5eee49b8a54628acfa4dc94ab26cfe3444419d7afd2e184b74f20342","last_reissued_at":"2026-07-05T10:06:35.857715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:35.857715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity and performance for two classes of noise-tolerant first-order algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ph. L. Toint, S. Gratton, S. Jerad","submitted_at":"2022-03-03T15:10:40Z","abstract_excerpt":"Two classes of algorithms for optimization in the presence of noise are presented, that do not require the evaluation of the objective function. The first generalizes the well-known Adagrad method. Its complexity is then analyzed as a function of its parameters. A second class of algorithms is then derived whose complexity is at least as good as that of the first class. Initial numerical experiments on finite-sum problems arising from deep-learning applications suggest that methods of the second class may outperform those of the first."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01757","kind":"arxiv","version":3},"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/2203.01757/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":"2203.01757","created_at":"2026-07-05T10:06:35.857769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01757v3","created_at":"2026-07-05T10:06:35.857769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01757","created_at":"2026-07-05T10:06:35.857769+00:00"},{"alias_kind":"pith_short_12","alias_value":"65F6HPC65ZE3","created_at":"2026-07-05T10:06:35.857769+00:00"},{"alias_kind":"pith_short_16","alias_value":"65F6HPC65ZE3RJKG","created_at":"2026-07-05T10:06:35.857769+00:00"},{"alias_kind":"pith_short_8","alias_value":"65F6HPC6","created_at":"2026-07-05T10:06:35.857769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08308","citing_title":"prunAdag: an adaptive pruning-aware gradient method","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK","json":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK.json","graph_json":"https://pith.science/api/pith-number/65F6HPC65ZE3RJKGFCWPUTOJJK/graph.json","events_json":"https://pith.science/api/pith-number/65F6HPC65ZE3RJKGFCWPUTOJJK/events.json","paper":"https://pith.science/paper/65F6HPC6"},"agent_actions":{"view_html":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK","download_json":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK.json","view_paper":"https://pith.science/paper/65F6HPC6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01757&json=true","fetch_graph":"https://pith.science/api/pith-number/65F6HPC65ZE3RJKGFCWPUTOJJK/graph.json","fetch_events":"https://pith.science/api/pith-number/65F6HPC65ZE3RJKGFCWPUTOJJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK/action/storage_attestation","attest_author":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK/action/author_attestation","sign_citation":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK/action/citation_signature","submit_replication":"https://pith.science/pith/65F6HPC65ZE3RJKGFCWPUTOJJK/action/replication_record"}},"created_at":"2026-07-05T10:06:35.857769+00:00","updated_at":"2026-07-05T10:06:35.857769+00:00"}