{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2RIGF5BZLXSODWFPBI63T3P4TY","short_pith_number":"pith:2RIGF5BZ","schema_version":"1.0","canonical_sha256":"d45062f4395de4e1d8af0a3db9edfc9e2ec857832345ad80e1fbc48332eb5a3a","source":{"kind":"arxiv","id":"1807.01695","version":2},"attestation_state":"computed","paper":{"title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Chris Junchi Li, Cong Fang, Tong Zhang, Zhouchen Lin","submitted_at":"2018-07-04T17:44:39Z","abstract_excerpt":"In this paper, we propose a new technique named \\textit{Stochastic Path-Integrated Differential EstimatoR} (SPIDER), which can be used to track many deterministic quantities of interest with significantly reduced computational cost. We apply SPIDER to two tasks, namely the stochastic first-order and zeroth-order methods. For stochastic first-order method, combining SPIDER with normalized gradient descent, we propose two new algorithms, namely SPIDER-SFO and SPIDER-SFO\\textsuperscript{+}, that solve non-convex stochastic optimization problems using stochastic gradients only. We provide sharp er"},"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":"1807.01695","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-04T17:44:39Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"910a1e1f51e63398d609a72c5f2668e371418aac6fb5883c39174ab5fc774328","abstract_canon_sha256":"86ef48bbaea309e68cb9d0bf04f817117657a1fe73e03204ede8ccd795a1ddee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:59.659539Z","signature_b64":"aJDoRlMfjvZ6TxVwqM/q+FZurpwEfRfmyBGddipQFArOZGS7VX7FszSEImk51/g07pt/fcs3lu+XAdql6UpaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d45062f4395de4e1d8af0a3db9edfc9e2ec857832345ad80e1fbc48332eb5a3a","last_reissued_at":"2026-05-18T00:02:59.658784Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:59.658784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path Integrated Differential Estimator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Chris Junchi Li, Cong Fang, Tong Zhang, Zhouchen Lin","submitted_at":"2018-07-04T17:44:39Z","abstract_excerpt":"In this paper, we propose a new technique named \\textit{Stochastic Path-Integrated Differential EstimatoR} (SPIDER), which can be used to track many deterministic quantities of interest with significantly reduced computational cost. We apply SPIDER to two tasks, namely the stochastic first-order and zeroth-order methods. For stochastic first-order method, combining SPIDER with normalized gradient descent, we propose two new algorithms, namely SPIDER-SFO and SPIDER-SFO\\textsuperscript{+}, that solve non-convex stochastic optimization problems using stochastic gradients only. We provide sharp er"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.01695","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":"1807.01695","created_at":"2026-05-18T00:02:59.658909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.01695v2","created_at":"2026-05-18T00:02:59.658909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.01695","created_at":"2026-05-18T00:02:59.658909+00:00"},{"alias_kind":"pith_short_12","alias_value":"2RIGF5BZLXSO","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2RIGF5BZLXSODWFP","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2RIGF5BZ","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":72,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28254","citing_title":"MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY","json":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY.json","graph_json":"https://pith.science/api/pith-number/2RIGF5BZLXSODWFPBI63T3P4TY/graph.json","events_json":"https://pith.science/api/pith-number/2RIGF5BZLXSODWFPBI63T3P4TY/events.json","paper":"https://pith.science/paper/2RIGF5BZ"},"agent_actions":{"view_html":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY","download_json":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY.json","view_paper":"https://pith.science/paper/2RIGF5BZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.01695&json=true","fetch_graph":"https://pith.science/api/pith-number/2RIGF5BZLXSODWFPBI63T3P4TY/graph.json","fetch_events":"https://pith.science/api/pith-number/2RIGF5BZLXSODWFPBI63T3P4TY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY/action/storage_attestation","attest_author":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY/action/author_attestation","sign_citation":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY/action/citation_signature","submit_replication":"https://pith.science/pith/2RIGF5BZLXSODWFPBI63T3P4TY/action/replication_record"}},"created_at":"2026-05-18T00:02:59.658909+00:00","updated_at":"2026-05-18T00:02:59.658909+00:00"}