{"id":"W4372266203","doi":"10.1109/icassp49357.2023.10094632","title":"Deep Proximal Gradient Method for Learned Convex Regularizers","year":2023,"lang":"en","type":"article","venue":"","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Subgradient method; Proximal Gradient Methods; Operator (biology); Penalty method; Mathematical optimization; Computer science; Gaussian; Gradient descent; Convex function; Regular polygon; Function (biology); Convergence (economics); Artificial intelligence; Algorithm; Mathematics; Artificial neural network","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":[0.0001395224,0.00009668017,0.0001298596,0.00008625452,0.00004066483,0.00002225912,0.00008895629,0.00005875691,0.00002090465],"category_scores_gemma":[0.00002280768,0.00008930052,0.00006676793,0.0001640917,0.00001384103,0.0000368644,0.0000240351,0.00006189715,0.00003182072],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001936886,"about_ca_system_score_gemma":0.000004442287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009231346,"about_ca_topic_score_gemma":0.000005010181,"domain_scores_codex":[0.9994407,0.0000134129,0.0001060786,0.000138997,0.00007251023,0.0002282593],"domain_scores_gemma":[0.9996742,0.00006826432,0.00001101133,0.0001805533,0.00003167284,0.00003432104],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009250468,0.00004900981,0.0001348527,0.0001898504,0.0004051999,0.00005261654,0.001121654,0.06739963,0.3735575,0.06781854,0.3339058,0.1552729],"study_design_scores_gemma":[0.0001612784,0.00003431411,0.00008598445,0.000009849953,0.00001120671,0.000003663887,0.00006239927,0.7613671,0.2105647,0.004717365,0.02285365,0.0001284649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007245066,0.00004498008,0.9807245,0.0002357264,0.0002214642,0.0003548272,0.000001396231,0.004208037,0.006963993],"genre_scores_gemma":[0.4791067,0.00004790707,0.51718,0.0002728217,0.0001420563,0.0001813871,0.00003249395,0.0001013659,0.002935295],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6939675,"threshold_uncertainty_score":0.364157,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0345452389760381,"score_gpt":0.291548444737975,"score_spread":0.2570032057619369,"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."}}