{"id":"W2913966198","doi":"10.1016/j.sigpro.2019.02.010","title":"Accelerated stochastic gradient descent with step size selection rules","year":2019,"lang":"en","type":"article","venue":"Signal Processing","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Stochastic gradient descent; PROX; Computer science; Gradient descent; Gradient method; Convergence (economics); Artificial intelligence; Algorithm; Mathematical optimization; Mathematics; Artificial neural network; Chemistry","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":[0.00004865723,0.0001679936,0.000151847,0.00006290889,0.00008129762,0.0001070117,0.00008486261,0.00005614092,0.00005750599],"category_scores_gemma":[0.000003622852,0.0001425343,0.00002273395,0.0002065837,0.00002115197,0.0001815187,0.00001403005,0.0001752297,0.00003148373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007660066,"about_ca_system_score_gemma":0.00003357757,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001034035,"about_ca_topic_score_gemma":0.000003945087,"domain_scores_codex":[0.9992454,0.00001297647,0.000133355,0.0001878699,0.0001671505,0.0002532254],"domain_scores_gemma":[0.9996998,0.00002636535,0.00003976608,0.0000840479,0.0000990672,0.00005100723],"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":[0.0002276613,0.0001244241,0.001779581,0.0003752486,0.0001459146,0.00002426785,0.0006908657,0.3939025,0.4273338,0.0001648239,0.0009463469,0.1742846],"study_design_scores_gemma":[0.0004798383,0.0002061285,0.00169992,0.0007524238,0.00004179615,0.00005531285,0.0001000041,0.8905869,0.1049528,0.0003671387,0.0002867001,0.0004710911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7738429,0.000292006,0.2230943,0.00001048173,0.00005813107,0.000221353,9.323876e-7,0.001069376,0.001410553],"genre_scores_gemma":[0.9944964,0.000002896124,0.005290195,0.00003245047,0.00006143487,0.00001007017,0.000003329867,0.00004463234,0.00005856916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4966844,"threshold_uncertainty_score":0.5812382,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01342216422020801,"score_gpt":0.215019254110561,"score_spread":0.201597089890353,"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."}}