{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:CURLG4QYKVEBMBJ7BHRLRYXYDH","short_pith_number":"pith:CURLG4QY","schema_version":"1.0","canonical_sha256":"1522b37218554816053f09e2b8e2f819c3c1f495ab9afc88b2bba205a4a41611","source":{"kind":"arxiv","id":"1705.05933","version":3},"attestation_state":"computed","paper":{"title":"Sub-sampled Cubic Regularization for Non-convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Jonas Moritz Kohler","submitted_at":"2017-05-16T21:44:44Z","abstract_excerpt":"We consider the minimization of non-convex functions that typically arise in machine learning. Specifically, we focus our attention on a variant of trust region methods known as cubic regularization. This approach is particularly attractive because it escapes strict saddle points and it provides stronger convergence guarantees than first- and second-order as well as classical trust region methods. However, it suffers from a high computational complexity that makes it impractical for large-scale learning. Here, we propose a novel method that uses sub-sampling to lower this computational cost. B"},"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":"1705.05933","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-16T21:44:44Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"d8716d846573f6378b8d266bfffa986e8298113b524845619a50bc9666a51732","abstract_canon_sha256":"6bed4077b27d0b3708ac07fe32ffea0f9089a06008ba8a38ba64cbafda43ce87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:06.928969Z","signature_b64":"Hc2AHZXhR5W09tdXjVQmFQDrm+ivWvU90Aj22xMnd9AxX4SX5WRtmPqZ9ZKfVDQPBA69NFJSkri8DvvPEX+ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1522b37218554816053f09e2b8e2f819c3c1f495ab9afc88b2bba205a4a41611","last_reissued_at":"2026-05-18T00:41:06.928495Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:06.928495Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-sampled Cubic Regularization for Non-convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurelien Lucchi, Jonas Moritz Kohler","submitted_at":"2017-05-16T21:44:44Z","abstract_excerpt":"We consider the minimization of non-convex functions that typically arise in machine learning. Specifically, we focus our attention on a variant of trust region methods known as cubic regularization. This approach is particularly attractive because it escapes strict saddle points and it provides stronger convergence guarantees than first- and second-order as well as classical trust region methods. However, it suffers from a high computational complexity that makes it impractical for large-scale learning. Here, we propose a novel method that uses sub-sampling to lower this computational cost. B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.05933","kind":"arxiv","version":3},"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":"1705.05933","created_at":"2026-05-18T00:41:06.928568+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.05933v3","created_at":"2026-05-18T00:41:06.928568+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.05933","created_at":"2026-05-18T00:41:06.928568+00:00"},{"alias_kind":"pith_short_12","alias_value":"CURLG4QYKVEB","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"CURLG4QYKVEBMBJ7","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"CURLG4QY","created_at":"2026-05-18T12:31:10.602751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11417","citing_title":"Combining Stochastic Adaptive Cubic Regularization with Negative Curvature for Nonconvex Optimization","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH","json":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH.json","graph_json":"https://pith.science/api/pith-number/CURLG4QYKVEBMBJ7BHRLRYXYDH/graph.json","events_json":"https://pith.science/api/pith-number/CURLG4QYKVEBMBJ7BHRLRYXYDH/events.json","paper":"https://pith.science/paper/CURLG4QY"},"agent_actions":{"view_html":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH","download_json":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH.json","view_paper":"https://pith.science/paper/CURLG4QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.05933&json=true","fetch_graph":"https://pith.science/api/pith-number/CURLG4QYKVEBMBJ7BHRLRYXYDH/graph.json","fetch_events":"https://pith.science/api/pith-number/CURLG4QYKVEBMBJ7BHRLRYXYDH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH/action/storage_attestation","attest_author":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH/action/author_attestation","sign_citation":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH/action/citation_signature","submit_replication":"https://pith.science/pith/CURLG4QYKVEBMBJ7BHRLRYXYDH/action/replication_record"}},"created_at":"2026-05-18T00:41:06.928568+00:00","updated_at":"2026-05-18T00:41:06.928568+00:00"}