{"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"}