{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FG7BUQAVJDVCUZTOPVZ6C4W5RX","short_pith_number":"pith:FG7BUQAV","schema_version":"1.0","canonical_sha256":"29be1a401548ea2a666e7d73e172dd8df0c7c56d6a4f43ce32e4d37bbdc89562","source":{"kind":"arxiv","id":"2410.20617","version":1},"attestation_state":"computed","paper":{"title":"A successive approximation method in functional spaces for hierarchical optimal control problems and its application to learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Getachew K. Befekadu","submitted_at":"2024-10-27T22:28:07Z","abstract_excerpt":"We consider a class of learning problem of point estimation for modeling high-dimensional nonlinear functions, whose learning dynamics is guided by model training dataset, while the estimated parameter in due course provides an acceptable prediction accuracy on a different model validation dataset. Here, we establish an evidential connection between such a learning problem and a hierarchical optimal control problem that provides a framework how to account appropriately for both generalization and regularization at the optimization stage. In particular, we consider the following two objectives:"},"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":"2410.20617","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2024-10-27T22:28:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"ace5f624b0e69bf9de5699df5e97f0a35637ebacdd6d14be84ca85214f15fcbf","abstract_canon_sha256":"d02e332fe1ebf6116d26d2a305bb32f9bcb9328d2e6d4acede3afaaf3151527d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:48.271150Z","signature_b64":"LiLNTcbJ4dpXiKV5t+HSKexasQVRJn1/H2fZdDNzYsBmEU4kb3SxN2vunTf8aHrIjKN7INP++O2d2Yv3nsYFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29be1a401548ea2a666e7d73e172dd8df0c7c56d6a4f43ce32e4d37bbdc89562","last_reissued_at":"2026-07-05T09:26:48.270665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:48.270665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A successive approximation method in functional spaces for hierarchical optimal control problems and its application to learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"math.OC","authors_text":"Getachew K. Befekadu","submitted_at":"2024-10-27T22:28:07Z","abstract_excerpt":"We consider a class of learning problem of point estimation for modeling high-dimensional nonlinear functions, whose learning dynamics is guided by model training dataset, while the estimated parameter in due course provides an acceptable prediction accuracy on a different model validation dataset. Here, we establish an evidential connection between such a learning problem and a hierarchical optimal control problem that provides a framework how to account appropriately for both generalization and regularization at the optimization stage. In particular, we consider the following two objectives:"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20617","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/2410.20617/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":"2410.20617","created_at":"2026-07-05T09:26:48.270720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20617v1","created_at":"2026-07-05T09:26:48.270720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20617","created_at":"2026-07-05T09:26:48.270720+00:00"},{"alias_kind":"pith_short_12","alias_value":"FG7BUQAVJDVC","created_at":"2026-07-05T09:26:48.270720+00:00"},{"alias_kind":"pith_short_16","alias_value":"FG7BUQAVJDVCUZTO","created_at":"2026-07-05T09:26:48.270720+00:00"},{"alias_kind":"pith_short_8","alias_value":"FG7BUQAV","created_at":"2026-07-05T09:26:48.270720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.16521","citing_title":"On characterizing optimal learning trajectories in a class of learning problems","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX","json":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX.json","graph_json":"https://pith.science/api/pith-number/FG7BUQAVJDVCUZTOPVZ6C4W5RX/graph.json","events_json":"https://pith.science/api/pith-number/FG7BUQAVJDVCUZTOPVZ6C4W5RX/events.json","paper":"https://pith.science/paper/FG7BUQAV"},"agent_actions":{"view_html":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX","download_json":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX.json","view_paper":"https://pith.science/paper/FG7BUQAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20617&json=true","fetch_graph":"https://pith.science/api/pith-number/FG7BUQAVJDVCUZTOPVZ6C4W5RX/graph.json","fetch_events":"https://pith.science/api/pith-number/FG7BUQAVJDVCUZTOPVZ6C4W5RX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX/action/storage_attestation","attest_author":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX/action/author_attestation","sign_citation":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX/action/citation_signature","submit_replication":"https://pith.science/pith/FG7BUQAVJDVCUZTOPVZ6C4W5RX/action/replication_record"}},"created_at":"2026-07-05T09:26:48.270720+00:00","updated_at":"2026-07-05T09:26:48.270720+00:00"}