{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RUXSZCGDQ5BYEGASPMGFIMWPEO","short_pith_number":"pith:RUXSZCGD","schema_version":"1.0","canonical_sha256":"8d2f2c88c387438218127b0c5432cf238175c23d7a719888d81a3de04c238af4","source":{"kind":"arxiv","id":"2406.15793","version":3},"attestation_state":"computed","paper":{"title":"Complexity of Adagrad and other first-order methods for nonconvex optimization problems with bounds constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Philippe L. Toint, Sadok Jerad, Serge Gratton","submitted_at":"2024-06-22T09:18:13Z","abstract_excerpt":"A parametric class of trust-region algorithms for constrained nonconvex optimization is analyzed, where the objective function is never computed. By defining appropriate first-order stationarity criteria, we are able to extend the Adagrad method to the newly considered problem and retrieve the standard complexity rate of the projected gradient method that uses both the gradient and objective function values. Furthermore, we propose an additional iteration-dependent scaling with slightly inferior theoretical guarantees. In both cases, the bounds are essentially sharp, and curvature information "},"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":"2406.15793","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-06-22T09:18:13Z","cross_cats_sorted":[],"title_canon_sha256":"ae8442f2d19bbf9fefe12f44683ec1e5d6a180105daa0b24ef56e4e6b2fb17ee","abstract_canon_sha256":"dc0ba3cf5a192deec2c5f603a8a413a2a996b98847ba120c2d8b27beb86455eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:30.641640Z","signature_b64":"An2p5NUZeY2N5qDaVu6BS/jwzOrY4cJqQUuD+Ko7/iqdWQzvpEdl+qPftOaFEGO/oeNTgGF/JwN7KiHzIgDJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d2f2c88c387438218127b0c5432cf238175c23d7a719888d81a3de04c238af4","last_reissued_at":"2026-07-05T09:29:30.641142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:30.641142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity of Adagrad and other first-order methods for nonconvex optimization problems with bounds constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Philippe L. Toint, Sadok Jerad, Serge Gratton","submitted_at":"2024-06-22T09:18:13Z","abstract_excerpt":"A parametric class of trust-region algorithms for constrained nonconvex optimization is analyzed, where the objective function is never computed. By defining appropriate first-order stationarity criteria, we are able to extend the Adagrad method to the newly considered problem and retrieve the standard complexity rate of the projected gradient method that uses both the gradient and objective function values. Furthermore, we propose an additional iteration-dependent scaling with slightly inferior theoretical guarantees. In both cases, the bounds are essentially sharp, and curvature information "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.15793","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/2406.15793/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":"2406.15793","created_at":"2026-07-05T09:29:30.641200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.15793v3","created_at":"2026-07-05T09:29:30.641200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.15793","created_at":"2026-07-05T09:29:30.641200+00:00"},{"alias_kind":"pith_short_12","alias_value":"RUXSZCGDQ5BY","created_at":"2026-07-05T09:29:30.641200+00:00"},{"alias_kind":"pith_short_16","alias_value":"RUXSZCGDQ5BYEGAS","created_at":"2026-07-05T09:29:30.641200+00:00"},{"alias_kind":"pith_short_8","alias_value":"RUXSZCGD","created_at":"2026-07-05T09:29:30.641200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11791","citing_title":"bAdag: an adaptive block coordinate gradient method for smooth nonconvex functions","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO","json":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO.json","graph_json":"https://pith.science/api/pith-number/RUXSZCGDQ5BYEGASPMGFIMWPEO/graph.json","events_json":"https://pith.science/api/pith-number/RUXSZCGDQ5BYEGASPMGFIMWPEO/events.json","paper":"https://pith.science/paper/RUXSZCGD"},"agent_actions":{"view_html":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO","download_json":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO.json","view_paper":"https://pith.science/paper/RUXSZCGD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.15793&json=true","fetch_graph":"https://pith.science/api/pith-number/RUXSZCGDQ5BYEGASPMGFIMWPEO/graph.json","fetch_events":"https://pith.science/api/pith-number/RUXSZCGDQ5BYEGASPMGFIMWPEO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO/action/storage_attestation","attest_author":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO/action/author_attestation","sign_citation":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO/action/citation_signature","submit_replication":"https://pith.science/pith/RUXSZCGDQ5BYEGASPMGFIMWPEO/action/replication_record"}},"created_at":"2026-07-05T09:29:30.641200+00:00","updated_at":"2026-07-05T09:29:30.641200+00:00"}