{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BLH3GKBYYG6ORUCMMLIJ3OMHCX","short_pith_number":"pith:BLH3GKBY","schema_version":"1.0","canonical_sha256":"0acfb32838c1bce8d04c62d09db98715f339f9c947908e98f8e268cc62b914c8","source":{"kind":"arxiv","id":"1806.07811","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Pan Xu, Quanquan Gu","submitted_at":"2018-06-20T16:01:09Z","abstract_excerpt":"We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with conventional stochastic variance reduced gradient (SVRG) algorithm that uses two reference points to construct a semi-stochastic gradient with diminishing variance in each iteration, our algorithm uses $K+1$ nested reference points to build a semi-stochastic gradient to further reduce its variance in each iteration. For smooth nonconvex functions, the proposed algorith"},"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":"1806.07811","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-20T16:01:09Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"7a20016e8112fc1aa88c4019e28d68e475953db512ba7bc72d72d70c821bb52f","abstract_canon_sha256":"8db023fd2e7c79f74b8e481d1aa64a617ff1e4c6223f9cf48dd55c4576aa0295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:53.815972Z","signature_b64":"XSUE/PelrtPbdF3yTCWZYI6NkG5KW2CQfkbKRPiOZO3rjhFLVBNdyR2v2x/aOBwtqptU/8tr5eXzm8B53fDdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0acfb32838c1bce8d04c62d09db98715f339f9c947908e98f8e268cc62b914c8","last_reissued_at":"2026-07-05T01:43:53.815478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:53.815478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Nested Variance Reduction for Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Pan Xu, Quanquan Gu","submitted_at":"2018-06-20T16:01:09Z","abstract_excerpt":"We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with conventional stochastic variance reduced gradient (SVRG) algorithm that uses two reference points to construct a semi-stochastic gradient with diminishing variance in each iteration, our algorithm uses $K+1$ nested reference points to build a semi-stochastic gradient to further reduce its variance in each iteration. For smooth nonconvex functions, the proposed algorith"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.07811","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/1806.07811/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":"1806.07811","created_at":"2026-07-05T01:43:53.815537+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.07811v2","created_at":"2026-07-05T01:43:53.815537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.07811","created_at":"2026-07-05T01:43:53.815537+00:00"},{"alias_kind":"pith_short_12","alias_value":"BLH3GKBYYG6O","created_at":"2026-07-05T01:43:53.815537+00:00"},{"alias_kind":"pith_short_16","alias_value":"BLH3GKBYYG6ORUCM","created_at":"2026-07-05T01:43:53.815537+00:00"},{"alias_kind":"pith_short_8","alias_value":"BLH3GKBY","created_at":"2026-07-05T01:43:53.815537+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09331","citing_title":"Dimension-Free Saddle-Point Escape in Muon","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX","json":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX.json","graph_json":"https://pith.science/api/pith-number/BLH3GKBYYG6ORUCMMLIJ3OMHCX/graph.json","events_json":"https://pith.science/api/pith-number/BLH3GKBYYG6ORUCMMLIJ3OMHCX/events.json","paper":"https://pith.science/paper/BLH3GKBY"},"agent_actions":{"view_html":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX","download_json":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX.json","view_paper":"https://pith.science/paper/BLH3GKBY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.07811&json=true","fetch_graph":"https://pith.science/api/pith-number/BLH3GKBYYG6ORUCMMLIJ3OMHCX/graph.json","fetch_events":"https://pith.science/api/pith-number/BLH3GKBYYG6ORUCMMLIJ3OMHCX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX/action/storage_attestation","attest_author":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX/action/author_attestation","sign_citation":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX/action/citation_signature","submit_replication":"https://pith.science/pith/BLH3GKBYYG6ORUCMMLIJ3OMHCX/action/replication_record"}},"created_at":"2026-07-05T01:43:53.815537+00:00","updated_at":"2026-07-05T01:43:53.815537+00:00"}