{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:5CMG5O3RYEPTHGSC2RYGFA2XZT","short_pith_number":"pith:5CMG5O3R","schema_version":"1.0","canonical_sha256":"e8986ebb71c11f339a42d470628357ccef377ef74dc000030b16f9bc0df271b3","source":{"kind":"arxiv","id":"1606.00511","version":2},"attestation_state":"computed","paper":{"title":"Distributed Hessian-Free Optimization for Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dheevatsa Mudigere, Martin Tak\\'a\\v{c}, Mikhail Smelyanskiy, Xi He","submitted_at":"2016-06-02T00:39:03Z","abstract_excerpt":"Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to non-covexity nature of the problem, it was observed that SGD slows down near saddle point. Recent empirical work claim that by detecting and escaping saddle point efficiently, it's more likely to improve training performance. With this objective, we revisit Hessian-free optimization method for deep networks. We also develop its distributed variant and demonstrate s"},"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":"1606.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-02T00:39:03Z","cross_cats_sorted":["cs.DC","math.OC"],"title_canon_sha256":"71abe0e3f228ce59a7c8dfbbc1abd0680d7e8c57c94b9ccfca818b990402e1b5","abstract_canon_sha256":"ce41c7c2d0889274a7c53b2e048dca1698f831d7e52a9e0824c86609fbdb6751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:50.155934Z","signature_b64":"qD2Kp5AiYdNrbQdJaTi+I/NZPgZRopesDKkG1v7cDozPdV7p1RMH54aThOucbkCVGQazbVHqDOLqlml9E43zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8986ebb71c11f339a42d470628357ccef377ef74dc000030b16f9bc0df271b3","last_reissued_at":"2026-05-18T00:52:50.155131Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:50.155131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Hessian-Free Optimization for Deep Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","math.OC"],"primary_cat":"cs.LG","authors_text":"Dheevatsa Mudigere, Martin Tak\\'a\\v{c}, Mikhail Smelyanskiy, Xi He","submitted_at":"2016-06-02T00:39:03Z","abstract_excerpt":"Training deep neural network is a high dimensional and a highly non-convex optimization problem. Stochastic gradient descent (SGD) algorithm and it's variations are the current state-of-the-art solvers for this task. However, due to non-covexity nature of the problem, it was observed that SGD slows down near saddle point. Recent empirical work claim that by detecting and escaping saddle point efficiently, it's more likely to improve training performance. With this objective, we revisit Hessian-free optimization method for deep networks. We also develop its distributed variant and demonstrate s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00511","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":"1606.00511","created_at":"2026-05-18T00:52:50.155261+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.00511v2","created_at":"2026-05-18T00:52:50.155261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00511","created_at":"2026-05-18T00:52:50.155261+00:00"},{"alias_kind":"pith_short_12","alias_value":"5CMG5O3RYEPT","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"5CMG5O3RYEPTHGSC","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"5CMG5O3R","created_at":"2026-05-18T12:30:01.593930+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/5CMG5O3RYEPTHGSC2RYGFA2XZT","json":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT.json","graph_json":"https://pith.science/api/pith-number/5CMG5O3RYEPTHGSC2RYGFA2XZT/graph.json","events_json":"https://pith.science/api/pith-number/5CMG5O3RYEPTHGSC2RYGFA2XZT/events.json","paper":"https://pith.science/paper/5CMG5O3R"},"agent_actions":{"view_html":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT","download_json":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT.json","view_paper":"https://pith.science/paper/5CMG5O3R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.00511&json=true","fetch_graph":"https://pith.science/api/pith-number/5CMG5O3RYEPTHGSC2RYGFA2XZT/graph.json","fetch_events":"https://pith.science/api/pith-number/5CMG5O3RYEPTHGSC2RYGFA2XZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT/action/storage_attestation","attest_author":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT/action/author_attestation","sign_citation":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT/action/citation_signature","submit_replication":"https://pith.science/pith/5CMG5O3RYEPTHGSC2RYGFA2XZT/action/replication_record"}},"created_at":"2026-05-18T00:52:50.155261+00:00","updated_at":"2026-05-18T00:52:50.155261+00:00"}