{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BMREARWYWKYMUI34NTR4PFFYYI","short_pith_number":"pith:BMREARWY","schema_version":"1.0","canonical_sha256":"0b224046d8b2b0ca237c6ce3c794b8c20496273536158aec6a0aa7819dfdf5f5","source":{"kind":"arxiv","id":"2312.13677","version":1},"attestation_state":"computed","paper":{"title":"Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, Ken Trotti, Rolf Krause, Samuel A. Cruz Alegr\\'ia","submitted_at":"2023-12-21T09:00:24Z","abstract_excerpt":"We propose to train neural networks (NNs) using a novel variant of the ``Additively Preconditioned Trust-region Strategy'' (APTS). The proposed method is based on a parallelizable additive domain decomposition approach applied to the neural network's parameters. Built upon the TR framework, the APTS method ensures global convergence towards a minimizer. Moreover, it eliminates the need for computationally expensive hyper-parameter tuning, as the TR algorithm automatically determines the step size in each iteration. We demonstrate the capabilities, strengths, and limitations of the proposed APT"},"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":"2312.13677","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2023-12-21T09:00:24Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"0328b0962ec9c28fc15751a59cc6f682551671953de3dac87843586f0a59e872","abstract_canon_sha256":"f20df9a0f63536ae5ef474b404a1b0656af1b3cfcb0b08c3a019abf1c4fc78dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:48.180649Z","signature_b64":"RSsVSZsE7LjpweNWQu+ooAOE6EHgSc6+HsapY84Xjk67TbDS9nAm0sOlpQVtDmeYvM++wwfvVy8yVGV775WcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b224046d8b2b0ca237c6ce3c794b8c20496273536158aec6a0aa7819dfdf5f5","last_reissued_at":"2026-07-05T07:26:48.180228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:48.180228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel Trust-Region Approaches in Neural Network Training: Beyond Traditional Methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Alena Kopani\\v{c}\\'akov\\'a, Ken Trotti, Rolf Krause, Samuel A. Cruz Alegr\\'ia","submitted_at":"2023-12-21T09:00:24Z","abstract_excerpt":"We propose to train neural networks (NNs) using a novel variant of the ``Additively Preconditioned Trust-region Strategy'' (APTS). The proposed method is based on a parallelizable additive domain decomposition approach applied to the neural network's parameters. Built upon the TR framework, the APTS method ensures global convergence towards a minimizer. Moreover, it eliminates the need for computationally expensive hyper-parameter tuning, as the TR algorithm automatically determines the step size in each iteration. We demonstrate the capabilities, strengths, and limitations of the proposed APT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13677","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/2312.13677/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":"2312.13677","created_at":"2026-07-05T07:26:48.180288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13677v1","created_at":"2026-07-05T07:26:48.180288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13677","created_at":"2026-07-05T07:26:48.180288+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMREARWYWKYM","created_at":"2026-07-05T07:26:48.180288+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMREARWYWKYMUI34","created_at":"2026-07-05T07:26:48.180288+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMREARWY","created_at":"2026-07-05T07:26:48.180288+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI","json":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI.json","graph_json":"https://pith.science/api/pith-number/BMREARWYWKYMUI34NTR4PFFYYI/graph.json","events_json":"https://pith.science/api/pith-number/BMREARWYWKYMUI34NTR4PFFYYI/events.json","paper":"https://pith.science/paper/BMREARWY"},"agent_actions":{"view_html":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI","download_json":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI.json","view_paper":"https://pith.science/paper/BMREARWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13677&json=true","fetch_graph":"https://pith.science/api/pith-number/BMREARWYWKYMUI34NTR4PFFYYI/graph.json","fetch_events":"https://pith.science/api/pith-number/BMREARWYWKYMUI34NTR4PFFYYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI/action/storage_attestation","attest_author":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI/action/author_attestation","sign_citation":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI/action/citation_signature","submit_replication":"https://pith.science/pith/BMREARWYWKYMUI34NTR4PFFYYI/action/replication_record"}},"created_at":"2026-07-05T07:26:48.180288+00:00","updated_at":"2026-07-05T07:26:48.180288+00:00"}