{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:GJWV5A32B3S5UIUGRQLETXQ7TQ","short_pith_number":"pith:GJWV5A32","schema_version":"1.0","canonical_sha256":"326d5e837a0ee5da22868c1649de1f9c1f551f2c9e4100c1a6c82058841adccf","source":{"kind":"arxiv","id":"1611.06310","version":2},"attestation_state":"computed","paper":{"title":"Local minima in training of neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Grzegorz Swirszcz, Razvan Pascanu, Wojciech Marian Czarnecki","submitted_at":"2016-11-19T05:49:22Z","abstract_excerpt":"There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do they not seem to be affected by bad local minima? It is widely believed that training of deep models using gradient methods works so well because the error surface either has no local minima, or if they exist they need to be close in value to the global minimum. It is known that such results hold under very strong assumptions which are not satisfied by real "},"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":"1611.06310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-11-19T05:49:22Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"ef4238dd8d3455892daa3a308299cf0ced0f384b8876d60e3ca5d5ab44630717","abstract_canon_sha256":"d7a976a4d2a4049742cd79f0cb57112d006c6901293447774c59edbcdebd06c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:35.309716Z","signature_b64":"Uwv1YfspSjO2MJKBXh+2GQEKM2uhDOMvvjpboizBaJIqYGGpFfkzTpMsKY61VUMgt9CI8+4ZorYvfvaRkLgnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"326d5e837a0ee5da22868c1649de1f9c1f551f2c9e4100c1a6c82058841adccf","last_reissued_at":"2026-05-18T00:50:35.308935Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:35.308935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local minima in training of neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Grzegorz Swirszcz, Razvan Pascanu, Wojciech Marian Czarnecki","submitted_at":"2016-11-19T05:49:22Z","abstract_excerpt":"There has been a lot of recent interest in trying to characterize the error surface of deep models. This stems from a long standing question. Given that deep networks are highly nonlinear systems optimized by local gradient methods, why do they not seem to be affected by bad local minima? It is widely believed that training of deep models using gradient methods works so well because the error surface either has no local minima, or if they exist they need to be close in value to the global minimum. It is known that such results hold under very strong assumptions which are not satisfied by real "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.06310","kind":"arxiv","version":2},"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":"1611.06310","created_at":"2026-05-18T00:50:35.309075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.06310v2","created_at":"2026-05-18T00:50:35.309075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.06310","created_at":"2026-05-18T00:50:35.309075+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJWV5A32B3S5","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJWV5A32B3S5UIUG","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJWV5A32","created_at":"2026-05-18T12:30:19.053100+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/GJWV5A32B3S5UIUGRQLETXQ7TQ","json":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ.json","graph_json":"https://pith.science/api/pith-number/GJWV5A32B3S5UIUGRQLETXQ7TQ/graph.json","events_json":"https://pith.science/api/pith-number/GJWV5A32B3S5UIUGRQLETXQ7TQ/events.json","paper":"https://pith.science/paper/GJWV5A32"},"agent_actions":{"view_html":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ","download_json":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ.json","view_paper":"https://pith.science/paper/GJWV5A32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.06310&json=true","fetch_graph":"https://pith.science/api/pith-number/GJWV5A32B3S5UIUGRQLETXQ7TQ/graph.json","fetch_events":"https://pith.science/api/pith-number/GJWV5A32B3S5UIUGRQLETXQ7TQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ/action/storage_attestation","attest_author":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ/action/author_attestation","sign_citation":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ/action/citation_signature","submit_replication":"https://pith.science/pith/GJWV5A32B3S5UIUGRQLETXQ7TQ/action/replication_record"}},"created_at":"2026-05-18T00:50:35.309075+00:00","updated_at":"2026-05-18T00:50:35.309075+00:00"}