{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:4G3DP3LUMBDKLDLHMODJJ2VYKZ","short_pith_number":"pith:4G3DP3LU","schema_version":"1.0","canonical_sha256":"e1b637ed746046a58d67638694eab856766cc293bc7c465063cdbaeb89cb37d4","source":{"kind":"arxiv","id":"1611.00756","version":2},"attestation_state":"computed","paper":{"title":"Accelerated Methods for Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Aaron Sidford, John C. Duchi, Oliver Hinder, Yair Carmon","submitted_at":"2016-11-02T19:58:30Z","abstract_excerpt":"We present an accelerated gradient method for non-convex optimization problems with Lipschitz continuous first and second derivatives. The method requires time $O(\\epsilon^{-7/4} \\log(1/ \\epsilon) )$ to find an $\\epsilon$-stationary point, meaning a point $x$ such that $\\|\\nabla f(x)\\| \\le \\epsilon$. The method improves upon the $O(\\epsilon^{-2} )$ complexity of gradient descent and provides the additional second-order guarantee that $\\nabla^2 f(x) \\succeq -O(\\epsilon^{1/2})I$ for the computed $x$. Furthermore, our method is Hessian free, i.e. it only requires gradient computations, and is the"},"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":"1611.00756","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2016-11-02T19:58:30Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"38a6fbc54f003db772c6372642b1a82cc1ffba95312a2a3b4c17bf58fea679f6","abstract_canon_sha256":"83f781d5bf1d5c49191282fa62ca3aceb28e56b8c7b34b7ffa8319ee70d596f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:33.828850Z","signature_b64":"gXczdv4yRBOBHHIWN8OlH2Dl/znKNp2GgiGVS2vfWJfIiGNwD67O6hQPnTOVapnRAE11NUEaUDeU1OwfrmLaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1b637ed746046a58d67638694eab856766cc293bc7c465063cdbaeb89cb37d4","last_reissued_at":"2026-05-18T00:51:33.828444Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:33.828444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Methods for Non-Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"math.OC","authors_text":"Aaron Sidford, John C. Duchi, Oliver Hinder, Yair Carmon","submitted_at":"2016-11-02T19:58:30Z","abstract_excerpt":"We present an accelerated gradient method for non-convex optimization problems with Lipschitz continuous first and second derivatives. The method requires time $O(\\epsilon^{-7/4} \\log(1/ \\epsilon) )$ to find an $\\epsilon$-stationary point, meaning a point $x$ such that $\\|\\nabla f(x)\\| \\le \\epsilon$. The method improves upon the $O(\\epsilon^{-2} )$ complexity of gradient descent and provides the additional second-order guarantee that $\\nabla^2 f(x) \\succeq -O(\\epsilon^{1/2})I$ for the computed $x$. Furthermore, our method is Hessian free, i.e. it only requires gradient computations, and is the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00756","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":"1611.00756","created_at":"2026-05-18T00:51:33.828513+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00756v2","created_at":"2026-05-18T00:51:33.828513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00756","created_at":"2026-05-18T00:51:33.828513+00:00"},{"alias_kind":"pith_short_12","alias_value":"4G3DP3LUMBDK","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_16","alias_value":"4G3DP3LUMBDKLDLH","created_at":"2026-05-18T12:29:58.707656+00:00"},{"alias_kind":"pith_short_8","alias_value":"4G3DP3LU","created_at":"2026-05-18T12:29:58.707656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.00918","citing_title":"Efficiency of Coordinate Descent Methods For Structured Nonconvex Optimization","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ","json":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ.json","graph_json":"https://pith.science/api/pith-number/4G3DP3LUMBDKLDLHMODJJ2VYKZ/graph.json","events_json":"https://pith.science/api/pith-number/4G3DP3LUMBDKLDLHMODJJ2VYKZ/events.json","paper":"https://pith.science/paper/4G3DP3LU"},"agent_actions":{"view_html":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ","download_json":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ.json","view_paper":"https://pith.science/paper/4G3DP3LU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00756&json=true","fetch_graph":"https://pith.science/api/pith-number/4G3DP3LUMBDKLDLHMODJJ2VYKZ/graph.json","fetch_events":"https://pith.science/api/pith-number/4G3DP3LUMBDKLDLHMODJJ2VYKZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ/action/storage_attestation","attest_author":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ/action/author_attestation","sign_citation":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ/action/citation_signature","submit_replication":"https://pith.science/pith/4G3DP3LUMBDKLDLHMODJJ2VYKZ/action/replication_record"}},"created_at":"2026-05-18T00:51:33.828513+00:00","updated_at":"2026-05-18T00:51:33.828513+00:00"}