{"id":"W4410327709","doi":"10.23952/jnva.9.2025.4.07","title":"Convergence analysis of a proximal stochastic gradient algorithm with adaptive sampling for non-convex and non-smooth composite optimization problems","year":2025,"lang":"en","type":"article","venue":"Journal of Nonlinear and Variational Analysis","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Research and Innovation Foundation; National Natural Science Foundation of China","keywords":"Convergence (economics); Proximal Gradient Methods; Mathematical optimization; Regular polygon; Sampling (signal processing); Mathematics; Algorithm; Composite number; Computer science; Convex optimization","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005111733,0.0001639559,0.0006344463,0.001708579,0.0001327443,0.00008518418,0.0002385907,0.00005951338,0.000004936617],"category_scores_gemma":[0.00005535525,0.0001318959,0.0002124349,0.003153603,0.00007294372,0.0003291851,0.0000701984,0.0001000803,3.704796e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004765101,"about_ca_system_score_gemma":0.0001527418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002739752,"about_ca_topic_score_gemma":0.000009983235,"domain_scores_codex":[0.9985,0.00003552322,0.000671308,0.0002936422,0.0003524386,0.0001470558],"domain_scores_gemma":[0.9973795,0.0003363509,0.0007745965,0.0001578595,0.001263381,0.00008833403],"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":[0.00008953745,0.0001678537,0.002567142,0.00002548758,0.004993699,7.379327e-7,0.0004181942,0.9877463,0.00005745279,0.002978658,0.000003676765,0.0009512528],"study_design_scores_gemma":[0.0006425,0.0003904152,0.01562793,0.0000640287,0.004765343,0.00000453432,0.00004410166,0.9777058,0.00005378592,0.000574716,0.000002060835,0.0001248271],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004043844,0.00007581242,0.9952949,0.0001822746,0.00004565356,0.0002853275,0.00005217368,0.000011631,0.000008333956],"genre_scores_gemma":[0.2637655,0.0000199256,0.7360907,0.00004072778,0.00002091926,0.00001414827,0.00003134805,0.000004539834,0.00001219345],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2597217,"threshold_uncertainty_score":0.537856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01293479474749572,"score_gpt":0.2567101088984031,"score_spread":0.2437753141509074,"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."}}