{"id":"W4360879278","doi":"10.1214/22-aos2246","title":"Sharp global convergence guarantees for iterative nonconvex optimization with random data","year":2023,"lang":"en","type":"article","venue":"The Annals of Statistics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Initialization; Subgradient method; Mathematical optimization; Sequence (biology); Rate of convergence; Gaussian; Applied mathematics; Algorithm; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001428039,0.00008837911,0.0001418692,0.00002097985,0.00004705965,0.00002256707,0.0002678658,0.00002259592,0.00001280845],"category_scores_gemma":[0.0001288955,0.00006191157,0.00001328334,0.0001647833,0.00006686349,0.00008290869,0.0000502094,0.00003568345,0.000004207527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000003790753,"about_ca_system_score_gemma":0.00001555609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001410082,"about_ca_topic_score_gemma":0.0000100096,"domain_scores_codex":[0.9994963,0.00001705183,0.0001451519,0.0001021618,0.00010751,0.0001318292],"domain_scores_gemma":[0.9990942,0.0002344452,0.00004864627,0.0003287116,0.0002760066,0.00001797598],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003140174,0.0000164751,0.00009487729,0.00009019482,0.0002142028,0.000009116247,0.0004273311,0.6116167,0.0002377741,0.007436089,0.3748192,0.004724008],"study_design_scores_gemma":[0.0003212192,0.00006807104,0.0001695915,0.00006700199,0.00002673154,0.000001434428,0.00006809087,0.9896573,0.004373812,0.003911112,0.001242091,0.00009353481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002341354,0.0001268445,0.9936303,0.0001335478,0.0001095022,0.0002434831,0.002945805,0.0002109616,0.0002581788],"genre_scores_gemma":[0.8635741,0.00128378,0.1337,0.0001967112,0.0001227198,0.00002756776,0.0009928545,0.00003693416,0.00006531445],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8612328,"threshold_uncertainty_score":0.252468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1322722702975442,"score_gpt":0.3511768969101887,"score_spread":0.2189046266126445,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}