{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:6MMUDA5K74AFLROBEMN7P6WWMF","short_pith_number":"pith:6MMUDA5K","schema_version":"1.0","canonical_sha256":"f3194183aaff0055c5c1231bf7fad6617429470372c0e23bc09be5e63daf590e","source":{"kind":"arxiv","id":"1410.1141","version":2},"attestation_state":"computed","paper":{"title":"On the Computational Efficiency of Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ohad Shamir, Roi Livni, Shai Shalev-Shwartz","submitted_at":"2014-10-05T10:54:07Z","abstract_excerpt":"It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g. ReLU), over-specification (i.e., train networks which are larger than needed), and regularization. In this paper we revisit the computational complexity of training neural networks from a modern perspective. We provide both positive and negative results, some of them yield new provably efficient and practical algorithms for training certain types of neural n"},"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":"1410.1141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-10-05T10:54:07Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"6e3e94e4071d16272c38c5f9e00ac0e78015f07a24dde974691f632daebebe8c","abstract_canon_sha256":"c193689a45c95bb4ac8b8e477c1f075a5b080fa91b18027ec16bd5179375eaef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:10.328706Z","signature_b64":"VMbip+eYv7jj1yu0XES+kXH6YmIt5oRJZPBau8bpykkaxfu1XMp9QffFkho+3z4ewu+ab7iHI5739UVBRPKsDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3194183aaff0055c5c1231bf7fad6617429470372c0e23bc09be5e63daf590e","last_reissued_at":"2026-05-18T02:39:10.327990Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:10.327990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Computational Efficiency of Training Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ohad Shamir, Roi Livni, Shai Shalev-Shwartz","submitted_at":"2014-10-05T10:54:07Z","abstract_excerpt":"It is well-known that neural networks are computationally hard to train. On the other hand, in practice, modern day neural networks are trained efficiently using SGD and a variety of tricks that include different activation functions (e.g. ReLU), over-specification (i.e., train networks which are larger than needed), and regularization. In this paper we revisit the computational complexity of training neural networks from a modern perspective. We provide both positive and negative results, some of them yield new provably efficient and practical algorithms for training certain types of neural n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.1141","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":"1410.1141","created_at":"2026-05-18T02:39:10.328115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1410.1141v2","created_at":"2026-05-18T02:39:10.328115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.1141","created_at":"2026-05-18T02:39:10.328115+00:00"},{"alias_kind":"pith_short_12","alias_value":"6MMUDA5K74AF","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"6MMUDA5K74AFLROB","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"6MMUDA5K","created_at":"2026-05-18T12:28:16.859392+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/6MMUDA5K74AFLROBEMN7P6WWMF","json":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF.json","graph_json":"https://pith.science/api/pith-number/6MMUDA5K74AFLROBEMN7P6WWMF/graph.json","events_json":"https://pith.science/api/pith-number/6MMUDA5K74AFLROBEMN7P6WWMF/events.json","paper":"https://pith.science/paper/6MMUDA5K"},"agent_actions":{"view_html":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF","download_json":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF.json","view_paper":"https://pith.science/paper/6MMUDA5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1410.1141&json=true","fetch_graph":"https://pith.science/api/pith-number/6MMUDA5K74AFLROBEMN7P6WWMF/graph.json","fetch_events":"https://pith.science/api/pith-number/6MMUDA5K74AFLROBEMN7P6WWMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF/action/storage_attestation","attest_author":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF/action/author_attestation","sign_citation":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF/action/citation_signature","submit_replication":"https://pith.science/pith/6MMUDA5K74AFLROBEMN7P6WWMF/action/replication_record"}},"created_at":"2026-05-18T02:39:10.328115+00:00","updated_at":"2026-05-18T02:39:10.328115+00:00"}