{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JU7OGDH2GFQABP6IYIHQZAA6EZ","short_pith_number":"pith:JU7OGDH2","schema_version":"1.0","canonical_sha256":"4d3ee30cfa316000bfc8c20f0c801e2679e19093a8dae31a449d46a883aae668","source":{"kind":"arxiv","id":"1906.02351","version":2},"attestation_state":"computed","paper":{"title":"On the Convergence of SARAH and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingcong Li, Georgios B. Giannakis, Meng Ma","submitted_at":"2019-06-05T23:02:46Z","abstract_excerpt":"The main theme of this work is a unifying algorithm, \\textbf{L}oop\\textbf{L}ess \\textbf{S}ARAH (L2S) for problems formulated as summation of $n$ individual loss functions. L2S broadens a recently developed variance reduction method known as SARAH. To find an $\\epsilon$-accurate solution, L2S enjoys a complexity of ${\\cal O}\\big( (n+\\kappa) \\ln (1/\\epsilon)\\big)$ for strongly convex problems. For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\\cal O}(n+ \\sqrt{n}/\\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\\c"},"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":"1906.02351","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-05T23:02:46Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"78fc45eab3df816ff9ecd2526f15106672bd2d78430afd0a3613ee6f41ca790e","abstract_canon_sha256":"6a0701d77836aa8cc2891067657153cf88a6818817818059ec3b5358a7670c0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:33:53.220459Z","signature_b64":"5SCzkwYUQWzJvKouA57kG1gauidpv4C33EZhTa7a86OkUmh9aHPLQDTS9lUBE5u63RMoayjYcCU7WAlm/K2iDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d3ee30cfa316000bfc8c20f0c801e2679e19093a8dae31a449d46a883aae668","last_reissued_at":"2026-07-05T00:33:53.219950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:33:53.219950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Convergence of SARAH and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingcong Li, Georgios B. Giannakis, Meng Ma","submitted_at":"2019-06-05T23:02:46Z","abstract_excerpt":"The main theme of this work is a unifying algorithm, \\textbf{L}oop\\textbf{L}ess \\textbf{S}ARAH (L2S) for problems formulated as summation of $n$ individual loss functions. L2S broadens a recently developed variance reduction method known as SARAH. To find an $\\epsilon$-accurate solution, L2S enjoys a complexity of ${\\cal O}\\big( (n+\\kappa) \\ln (1/\\epsilon)\\big)$ for strongly convex problems. For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\\cal O}(n+ \\sqrt{n}/\\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\\c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.02351","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/1906.02351/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":"1906.02351","created_at":"2026-07-05T00:33:53.220010+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.02351v2","created_at":"2026-07-05T00:33:53.220010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.02351","created_at":"2026-07-05T00:33:53.220010+00:00"},{"alias_kind":"pith_short_12","alias_value":"JU7OGDH2GFQA","created_at":"2026-07-05T00:33:53.220010+00:00"},{"alias_kind":"pith_short_16","alias_value":"JU7OGDH2GFQABP6I","created_at":"2026-07-05T00:33:53.220010+00:00"},{"alias_kind":"pith_short_8","alias_value":"JU7OGDH2","created_at":"2026-07-05T00:33:53.220010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.13046","citing_title":"Variance-Reduced Fast Operator Splitting Methods for Generalized Equations","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ","json":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ.json","graph_json":"https://pith.science/api/pith-number/JU7OGDH2GFQABP6IYIHQZAA6EZ/graph.json","events_json":"https://pith.science/api/pith-number/JU7OGDH2GFQABP6IYIHQZAA6EZ/events.json","paper":"https://pith.science/paper/JU7OGDH2"},"agent_actions":{"view_html":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ","download_json":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ.json","view_paper":"https://pith.science/paper/JU7OGDH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.02351&json=true","fetch_graph":"https://pith.science/api/pith-number/JU7OGDH2GFQABP6IYIHQZAA6EZ/graph.json","fetch_events":"https://pith.science/api/pith-number/JU7OGDH2GFQABP6IYIHQZAA6EZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ/action/storage_attestation","attest_author":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ/action/author_attestation","sign_citation":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ/action/citation_signature","submit_replication":"https://pith.science/pith/JU7OGDH2GFQABP6IYIHQZAA6EZ/action/replication_record"}},"created_at":"2026-07-05T00:33:53.220010+00:00","updated_at":"2026-07-05T00:33:53.220010+00:00"}