{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5C5LC7Z6WUG4EHCAVWSUPIWXFF","short_pith_number":"pith:5C5LC7Z6","schema_version":"1.0","canonical_sha256":"e8bab17f3eb50dc21c40ada547a2d72968aac58bf4332687eb5df52f5c72e85d","source":{"kind":"arxiv","id":"2006.11648","version":2},"attestation_state":"computed","paper":{"title":"Training (Overparametrized) Neural Networks in Near-Linear Time","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Binghui Peng, Jan van den Brand, Omri Weinstein, Zhao Song","submitted_at":"2020-06-20T20:26:14Z","abstract_excerpt":"The slow convergence rate and pathological curvature issues of first-order gradient methods for training deep neural networks, initiated an ongoing effort for developing faster $\\mathit{second}$-$\\mathit{order}$ optimization algorithms beyond SGD, without compromising the generalization error. Despite their remarkable convergence rate ($\\mathit{independent}$ of the training batch size $n$), second-order algorithms incur a daunting slowdown in the $\\mathit{cost}$ $\\mathit{per}$ $\\mathit{iteration}$ (inverting the Hessian matrix of the loss function), which renders them impractical. Very recentl"},"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":"2006.11648","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-20T20:26:14Z","cross_cats_sorted":["cs.DS","stat.ML"],"title_canon_sha256":"8ecdb3a087af65c11e32a04c55e19d0ff35b7eedd71ed4955817b3298231da72","abstract_canon_sha256":"68735dfa683deda1a5047eac71b04cd66fb2fb603bc605dc7c5fa082b7fad00d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:10.400755Z","signature_b64":"ZQ/9hsMrYGT9lW82aeadM6zWMZ0MYwjjDZqH9ByvGAV6wNM03tmK8k63KcE5jYRYcp4oqf/8FpPYf5mYuZJ5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8bab17f3eb50dc21c40ada547a2d72968aac58bf4332687eb5df52f5c72e85d","last_reissued_at":"2026-07-05T01:58:10.400199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:10.400199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training (Overparametrized) Neural Networks in Near-Linear Time","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DS","stat.ML"],"primary_cat":"cs.LG","authors_text":"Binghui Peng, Jan van den Brand, Omri Weinstein, Zhao Song","submitted_at":"2020-06-20T20:26:14Z","abstract_excerpt":"The slow convergence rate and pathological curvature issues of first-order gradient methods for training deep neural networks, initiated an ongoing effort for developing faster $\\mathit{second}$-$\\mathit{order}$ optimization algorithms beyond SGD, without compromising the generalization error. Despite their remarkable convergence rate ($\\mathit{independent}$ of the training batch size $n$), second-order algorithms incur a daunting slowdown in the $\\mathit{cost}$ $\\mathit{per}$ $\\mathit{iteration}$ (inverting the Hessian matrix of the loss function), which renders them impractical. Very recentl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11648","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11648/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":"2006.11648","created_at":"2026-07-05T01:58:10.400264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11648v2","created_at":"2026-07-05T01:58:10.400264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11648","created_at":"2026-07-05T01:58:10.400264+00:00"},{"alias_kind":"pith_short_12","alias_value":"5C5LC7Z6WUG4","created_at":"2026-07-05T01:58:10.400264+00:00"},{"alias_kind":"pith_short_16","alias_value":"5C5LC7Z6WUG4EHCA","created_at":"2026-07-05T01:58:10.400264+00:00"},{"alias_kind":"pith_short_8","alias_value":"5C5LC7Z6","created_at":"2026-07-05T01:58:10.400264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12441","citing_title":"Numerical Pruning for Efficient Autoregressive Models","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF","json":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF.json","graph_json":"https://pith.science/api/pith-number/5C5LC7Z6WUG4EHCAVWSUPIWXFF/graph.json","events_json":"https://pith.science/api/pith-number/5C5LC7Z6WUG4EHCAVWSUPIWXFF/events.json","paper":"https://pith.science/paper/5C5LC7Z6"},"agent_actions":{"view_html":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF","download_json":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF.json","view_paper":"https://pith.science/paper/5C5LC7Z6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11648&json=true","fetch_graph":"https://pith.science/api/pith-number/5C5LC7Z6WUG4EHCAVWSUPIWXFF/graph.json","fetch_events":"https://pith.science/api/pith-number/5C5LC7Z6WUG4EHCAVWSUPIWXFF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF/action/storage_attestation","attest_author":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF/action/author_attestation","sign_citation":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF/action/citation_signature","submit_replication":"https://pith.science/pith/5C5LC7Z6WUG4EHCAVWSUPIWXFF/action/replication_record"}},"created_at":"2026-07-05T01:58:10.400264+00:00","updated_at":"2026-07-05T01:58:10.400264+00:00"}