{"id":"W2075709901","doi":"10.1007/s10013-013-0055-x","title":"Faster Gradient Descent and the Efficient Recovery of Images","year":2013,"lang":"en","type":"article","venue":"Vietnam Journal of Mathematics","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Deblurring; Gradient descent; Slowness; Mathematics; Method of steepest descent; Context (archaeology); Mathematical optimization; Descent (aeronautics); Nonlinear conjugate gradient method; Smoothing; Stochastic gradient descent; Descent direction; Gradient method; Algorithm; Image restoration; Computer science; Image (mathematics); Artificial intelligence; Image processing; Artificial neural network; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001398386,0.0007421153,0.0009724851,0.0007397915,0.0003746845,0.0009190023,0.0008699449,0.001374456,0.002079261],"category_scores_gemma":[0.005751155,0.0006558335,0.0005456242,0.0008641672,0.001337804,0.002155591,0.001490402,0.001899976,0.0005892965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006930059,"about_ca_system_score_gemma":0.001116002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004476082,"about_ca_topic_score_gemma":0.004763191,"domain_scores_codex":[0.9994648,0.0002061158,0.0000223517,0.00007104224,0.0001778062,0.00005785036],"domain_scores_gemma":[0.9984933,0.0009510662,0.0001186233,0.0002089466,0.0001762632,0.00005175764],"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":[0.0003823076,0.00008397608,0.0003943392,0.0001923656,0.0000689015,0.000150111,0.0001822948,0.5682844,0.01804695,0.2649903,0.008257806,0.1389663],"study_design_scores_gemma":[0.0000138512,0.00001527748,0.00006641749,0.000005086103,0.000002991163,0.00002683361,0.000006477861,0.9742994,0.001225018,0.0234098,0.0009229795,0.000005825454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0185889,0.0004491041,0.9781822,0.0006098195,0.00009007069,0.00002137327,0.00005565683,0.0001588511,0.001843997],"genre_scores_gemma":[0.3354371,0.0009855942,0.6475073,0.00025599,0.0002212729,0.0001184566,0.0002726281,0.0002525992,0.0149491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004476082,"threshold_uncertainty_score":0.008900046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00965784556237763,"score_gpt":0.2003570006393703,"score_spread":0.1906991550769927,"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."}}