{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:STN76QIYC6DAUMLFKWPAEJTIZE","short_pith_number":"pith:STN76QIY","schema_version":"1.0","canonical_sha256":"94dbff411817860a3165559e022668c90badf93ebbbc2b1e3fb759e4f043f2ff","source":{"kind":"arxiv","id":"1606.00602","version":2},"attestation_state":"computed","paper":{"title":"Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"stat.ML","authors_text":"Dacheng Tao, Xiyu Yu","submitted_at":"2016-06-02T09:59:16Z","abstract_excerpt":"Here we study non-convex composite optimization: first, a finite-sum of smooth but non-convex functions, and second, a general function that admits a simple proximal mapping. Most research on stochastic methods for composite optimization assumes convexity or strong convexity of each function. In this paper, we extend this problem into the non-convex setting using variance reduction techniques, such as prox-SVRG and prox-SAGA. We prove that, with a constant step size, both prox-SVRG and prox-SAGA are suitable for non-convex composite optimization, and help the problem converge to a stationary p"},"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":"1606.00602","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-06-02T09:59:16Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"54d1399218ba669b702afd7398d723b7e0a5cc99848341349474d617c7c8b479","abstract_canon_sha256":"8c23a250594e2a35e2422311f9cedecbed59aa897ff2fe55248902f956c0ea93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:49.746529Z","signature_b64":"Isbm3Wf0NtXitgHqYAjkua+eOj6O2TFFQ1lOAo8rlD96vDKWQ8g3jaC3S6bTnZTg0zMTUfeDwH4IQSocz5gSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94dbff411817860a3165559e022668c90badf93ebbbc2b1e3fb759e4f043f2ff","last_reissued_at":"2026-05-18T01:04:49.745952Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:49.745952Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variance-Reduced Proximal Stochastic Gradient Descent for Non-convex Composite optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"stat.ML","authors_text":"Dacheng Tao, Xiyu Yu","submitted_at":"2016-06-02T09:59:16Z","abstract_excerpt":"Here we study non-convex composite optimization: first, a finite-sum of smooth but non-convex functions, and second, a general function that admits a simple proximal mapping. Most research on stochastic methods for composite optimization assumes convexity or strong convexity of each function. In this paper, we extend this problem into the non-convex setting using variance reduction techniques, such as prox-SVRG and prox-SAGA. We prove that, with a constant step size, both prox-SVRG and prox-SAGA are suitable for non-convex composite optimization, and help the problem converge to a stationary p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.00602","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":"1606.00602","created_at":"2026-05-18T01:04:49.746036+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.00602v2","created_at":"2026-05-18T01:04:49.746036+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.00602","created_at":"2026-05-18T01:04:49.746036+00:00"},{"alias_kind":"pith_short_12","alias_value":"STN76QIYC6DA","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_16","alias_value":"STN76QIYC6DAUMLF","created_at":"2026-05-18T12:30:44.179134+00:00"},{"alias_kind":"pith_short_8","alias_value":"STN76QIY","created_at":"2026-05-18T12:30:44.179134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE","json":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE.json","graph_json":"https://pith.science/api/pith-number/STN76QIYC6DAUMLFKWPAEJTIZE/graph.json","events_json":"https://pith.science/api/pith-number/STN76QIYC6DAUMLFKWPAEJTIZE/events.json","paper":"https://pith.science/paper/STN76QIY"},"agent_actions":{"view_html":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE","download_json":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE.json","view_paper":"https://pith.science/paper/STN76QIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.00602&json=true","fetch_graph":"https://pith.science/api/pith-number/STN76QIYC6DAUMLFKWPAEJTIZE/graph.json","fetch_events":"https://pith.science/api/pith-number/STN76QIYC6DAUMLFKWPAEJTIZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE/action/storage_attestation","attest_author":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE/action/author_attestation","sign_citation":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE/action/citation_signature","submit_replication":"https://pith.science/pith/STN76QIYC6DAUMLFKWPAEJTIZE/action/replication_record"}},"created_at":"2026-05-18T01:04:49.746036+00:00","updated_at":"2026-05-18T01:04:49.746036+00:00"}