{"id":"W2787899424","doi":"10.1137/17m1136225","title":"Learning Theory of Randomized Sparse Kaczmarz Method","year":2018,"lang":"en","type":"article","venue":"SIAM Journal on Imaging Sciences","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"Research Grants Council, University Grants Committee; National Natural Science Foundation of China","keywords":"Mathematics; Bregman divergence; Compressed sensing; Convergence (economics); Convexity; Thresholding; Sequence (biology); Generalization; Combinatorics; Function (biology); Applied mathematics; Algorithm; Discrete mathematics; Mathematical analysis; Artificial intelligence; Computer science; Image (mathematics)","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":[0.003985188,0.0001247381,0.0003397188,0.0002836997,0.0002653406,0.0001143888,0.0002989398,0.00002255735,0.00006952877],"category_scores_gemma":[0.0004026774,0.00008939515,0.0001403497,0.0002706985,0.0006511254,0.0002080126,0.00002820586,0.0002908105,0.0000128238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001919483,"about_ca_system_score_gemma":0.0000297873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003407878,"about_ca_topic_score_gemma":2.256344e-7,"domain_scores_codex":[0.998602,0.0003838428,0.0003160869,0.0001326873,0.0003212374,0.0002441109],"domain_scores_gemma":[0.9990253,0.0005322722,0.0001515902,0.0001084836,0.0001223218,0.00006001832],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005803436,0.0001418749,0.002726873,0.00005030388,0.000517937,0.0001627038,0.007326672,0.1044359,0.1641503,0.07643493,0.01631175,0.6219373],"study_design_scores_gemma":[0.01501084,0.0004658088,0.0003311234,0.00104108,0.0001278599,0.0006924671,0.001323027,0.4680181,0.3618485,0.1421771,0.00829733,0.0006667465],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1839592,0.001713545,0.6435854,0.0004582052,0.00190891,0.0002189936,7.493767e-7,0.0006555069,0.1674994],"genre_scores_gemma":[0.9575101,0.0001178078,0.04189283,0.0001107439,0.0002427262,0.00000137911,8.537516e-8,0.0000133704,0.0001109616],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7735509,"threshold_uncertainty_score":0.3645428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01831216625139827,"score_gpt":0.2959874223467209,"score_spread":0.2776752560953227,"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."}}