{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:SYV4PQ3HGCHMB6LLRGTWUIR6OM","short_pith_number":"pith:SYV4PQ3H","schema_version":"1.0","canonical_sha256":"962bc7c367308ec0f96b89a76a223e732b236d754bc6fb8df35fe1c67e9fcb95","source":{"kind":"arxiv","id":"1905.00529","version":1},"attestation_state":"computed","paper":{"title":"Stabilized SVRG: Simple 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":"Rong Ge, Weiyao Wang, Xiang Wang, Zhize Li","submitted_at":"2019-05-01T23:44:26Z","abstract_excerpt":"Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However, in nonconvex optimization it is often crucial to find a second-order stationary point (with small gradient and almost PSD hessian). In this paper, we show that Stabilized SVRG (a simple variant of SVRG) can find an $\\epsilon$-second-order stationary point using only $\\widetilde{O}(n^{2/3}/\\epsilon^2+n/\\epsilon^{1.5})$ stochastic gradients. To our best knowl"},"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":"1905.00529","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-01T23:44:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"77631a262078a8c4d5bd8d4f3c0a6893f711fc9201c3ce46ae570477af13d8fb","abstract_canon_sha256":"61426c44d74e489cc25492bfb936c2c060c605077a3d2cd85924986f6aeb39ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:11.623570Z","signature_b64":"rIN0DsorUyqgfyqXpFpmsVfQPiRrYA0m6ldTN36UlF3YinE4SpvPfGAyKTInwuuz5Psbq5rDNBmRxwJla4GDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"962bc7c367308ec0f96b89a76a223e732b236d754bc6fb8df35fe1c67e9fcb95","last_reissued_at":"2026-05-17T23:47:11.623207Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:11.623207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilized SVRG: Simple 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":"Rong Ge, Weiyao Wang, Xiang Wang, Zhize Li","submitted_at":"2019-05-01T23:44:26Z","abstract_excerpt":"Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However, in nonconvex optimization it is often crucial to find a second-order stationary point (with small gradient and almost PSD hessian). In this paper, we show that Stabilized SVRG (a simple variant of SVRG) can find an $\\epsilon$-second-order stationary point using only $\\widetilde{O}(n^{2/3}/\\epsilon^2+n/\\epsilon^{1.5})$ stochastic gradients. To our best knowl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.00529","kind":"arxiv","version":1},"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":"1905.00529","created_at":"2026-05-17T23:47:11.623261+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.00529v1","created_at":"2026-05-17T23:47:11.623261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.00529","created_at":"2026-05-17T23:47:11.623261+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYV4PQ3HGCHM","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYV4PQ3HGCHMB6LL","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYV4PQ3H","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.01848","citing_title":"Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM","json":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM.json","graph_json":"https://pith.science/api/pith-number/SYV4PQ3HGCHMB6LLRGTWUIR6OM/graph.json","events_json":"https://pith.science/api/pith-number/SYV4PQ3HGCHMB6LLRGTWUIR6OM/events.json","paper":"https://pith.science/paper/SYV4PQ3H"},"agent_actions":{"view_html":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM","download_json":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM.json","view_paper":"https://pith.science/paper/SYV4PQ3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.00529&json=true","fetch_graph":"https://pith.science/api/pith-number/SYV4PQ3HGCHMB6LLRGTWUIR6OM/graph.json","fetch_events":"https://pith.science/api/pith-number/SYV4PQ3HGCHMB6LLRGTWUIR6OM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM/action/storage_attestation","attest_author":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM/action/author_attestation","sign_citation":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM/action/citation_signature","submit_replication":"https://pith.science/pith/SYV4PQ3HGCHMB6LLRGTWUIR6OM/action/replication_record"}},"created_at":"2026-05-17T23:47:11.623261+00:00","updated_at":"2026-05-17T23:47:11.623261+00:00"}