{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:3HZU3V2VFWVOITVNJD6SHGTFC2","short_pith_number":"pith:3HZU3V2V","schema_version":"1.0","canonical_sha256":"d9f34dd7552daae44ead48fd239a65168348a8c23557d9ded999bf087eafee4b","source":{"kind":"arxiv","id":"1805.09214","version":1},"attestation_state":"computed","paper":{"title":"A Unified Framework for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Fischione, Hadi Ghauch, Hossein Shokri-Ghadikolaei, Mikael Skoglund","submitted_at":"2018-05-23T15:13:56Z","abstract_excerpt":"The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for training different types of DNNs, and establish its convergence for arbitrary loss, activation, and regularization functions, assumed to be smooth. We show that framework generalizes well-known first- and second-order training methods, and thus allows us to show the convergence of these methods for various DNN architectures and learning tasks, as a special case of "},"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":"1805.09214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T15:13:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"dda1d75b21b839e8f362bfd36d591292aae73ef4266047d1d1e8958e4f0655b6","abstract_canon_sha256":"7f24f7816db0f5319d38d3b65abbcfc8576b063d39c94585d892fca29fb11864"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:08.221248Z","signature_b64":"7ODKo0JBvL+GZKXofX4vvu/ApeSilBlUYEuMh5U+HDk5BBZpqbjX9udGxhjTFqUsbqvl8eE0eiwDT36RbqqXAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9f34dd7552daae44ead48fd239a65168348a8c23557d9ded999bf087eafee4b","last_reissued_at":"2026-05-18T00:15:08.220699Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:08.220699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Framework for Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carlo Fischione, Hadi Ghauch, Hossein Shokri-Ghadikolaei, Mikael Skoglund","submitted_at":"2018-05-23T15:13:56Z","abstract_excerpt":"The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for training different types of DNNs, and establish its convergence for arbitrary loss, activation, and regularization functions, assumed to be smooth. We show that framework generalizes well-known first- and second-order training methods, and thus allows us to show the convergence of these methods for various DNN architectures and learning tasks, as a special case of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09214","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":""},"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":"1805.09214","created_at":"2026-05-18T00:15:08.220785+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.09214v1","created_at":"2026-05-18T00:15:08.220785+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09214","created_at":"2026-05-18T00:15:08.220785+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HZU3V2VFWVO","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HZU3V2VFWVOITVN","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HZU3V2V","created_at":"2026-05-18T12:32:02.567920+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/3HZU3V2VFWVOITVNJD6SHGTFC2","json":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2.json","graph_json":"https://pith.science/api/pith-number/3HZU3V2VFWVOITVNJD6SHGTFC2/graph.json","events_json":"https://pith.science/api/pith-number/3HZU3V2VFWVOITVNJD6SHGTFC2/events.json","paper":"https://pith.science/paper/3HZU3V2V"},"agent_actions":{"view_html":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2","download_json":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2.json","view_paper":"https://pith.science/paper/3HZU3V2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.09214&json=true","fetch_graph":"https://pith.science/api/pith-number/3HZU3V2VFWVOITVNJD6SHGTFC2/graph.json","fetch_events":"https://pith.science/api/pith-number/3HZU3V2VFWVOITVNJD6SHGTFC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2/action/storage_attestation","attest_author":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2/action/author_attestation","sign_citation":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2/action/citation_signature","submit_replication":"https://pith.science/pith/3HZU3V2VFWVOITVNJD6SHGTFC2/action/replication_record"}},"created_at":"2026-05-18T00:15:08.220785+00:00","updated_at":"2026-05-18T00:15:08.220785+00:00"}