{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JDWNFNBLVDM5APYWYS27DDDNFK","short_pith_number":"pith:JDWNFNBL","schema_version":"1.0","canonical_sha256":"48ecd2b42ba8d9d03f16c4b5f18c6d2aa2eedb61e3d9c47df9fc2c910d8aedd9","source":{"kind":"arxiv","id":"2606.10383","version":1},"attestation_state":"computed","paper":{"title":"A stochastic gradient algorithm for non-separable optimization with convergence guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Ruofan Wu, Yingzhou Li","submitted_at":"2026-06-09T03:48:27Z","abstract_excerpt":"We study non-separable objectives in which the loss depend on dataset-level quantities. We introduce an SGD-style framework that employs two batch-gradient constructs: the ideal per-batch gradient `$G$' and a cached surrogate `$H$' for cases where full-data terms are expensive.\n  Notably, in the sample-wise separable case, our method reduces to standard mini-batch SGD. Our main contribution is a unified local convergence theory: under mild smoothness and Jacobian-boundedness assumptions,\n  we prove local linear convergence under local strong convexity and local $O(1/k)$ sublinear convergence u"},"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":"2606.10383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-06-09T03:48:27Z","cross_cats_sorted":["cs.NA","math.NA"],"title_canon_sha256":"1b91c15589be9dbb3cd268fa34ae5f375c8df3f92a1dcd63a177ebaa00e80b6d","abstract_canon_sha256":"d102fdc2afe329a19f5db292308a2592d137a35fa82f2ca7bb6219bc9a5a521c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:15.141666Z","signature_b64":"Arwb1f0LImZrOKcrXG1GUTQzANtITGU7Eskv+TKt+MmmJ9woaMJd6k/5DTPHO5e/waF4mXCN7FLswgwVNNUGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48ecd2b42ba8d9d03f16c4b5f18c6d2aa2eedb61e3d9c47df9fc2c910d8aedd9","last_reissued_at":"2026-06-10T01:10:15.140845Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:15.140845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A stochastic gradient algorithm for non-separable optimization with convergence guarantee","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NA","math.NA"],"primary_cat":"math.OC","authors_text":"Ruofan Wu, Yingzhou Li","submitted_at":"2026-06-09T03:48:27Z","abstract_excerpt":"We study non-separable objectives in which the loss depend on dataset-level quantities. We introduce an SGD-style framework that employs two batch-gradient constructs: the ideal per-batch gradient `$G$' and a cached surrogate `$H$' for cases where full-data terms are expensive.\n  Notably, in the sample-wise separable case, our method reduces to standard mini-batch SGD. Our main contribution is a unified local convergence theory: under mild smoothness and Jacobian-boundedness assumptions,\n  we prove local linear convergence under local strong convexity and local $O(1/k)$ sublinear convergence u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10383","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.10383/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":"2606.10383","created_at":"2026-06-10T01:10:15.140983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10383v1","created_at":"2026-06-10T01:10:15.140983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10383","created_at":"2026-06-10T01:10:15.140983+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDWNFNBLVDM5","created_at":"2026-06-10T01:10:15.140983+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDWNFNBLVDM5APYW","created_at":"2026-06-10T01:10:15.140983+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDWNFNBL","created_at":"2026-06-10T01:10:15.140983+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/JDWNFNBLVDM5APYWYS27DDDNFK","json":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK.json","graph_json":"https://pith.science/api/pith-number/JDWNFNBLVDM5APYWYS27DDDNFK/graph.json","events_json":"https://pith.science/api/pith-number/JDWNFNBLVDM5APYWYS27DDDNFK/events.json","paper":"https://pith.science/paper/JDWNFNBL"},"agent_actions":{"view_html":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK","download_json":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK.json","view_paper":"https://pith.science/paper/JDWNFNBL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10383&json=true","fetch_graph":"https://pith.science/api/pith-number/JDWNFNBLVDM5APYWYS27DDDNFK/graph.json","fetch_events":"https://pith.science/api/pith-number/JDWNFNBLVDM5APYWYS27DDDNFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK/action/storage_attestation","attest_author":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK/action/author_attestation","sign_citation":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK/action/citation_signature","submit_replication":"https://pith.science/pith/JDWNFNBLVDM5APYWYS27DDDNFK/action/replication_record"}},"created_at":"2026-06-10T01:10:15.140983+00:00","updated_at":"2026-06-10T01:10:15.140983+00:00"}