{"id":"W4247879929","doi":"10.1109/.2001.981010","title":"Law of the iterated logarithm for a constant-gain linear stochastic gradient algorithm","year":2002,"lang":"en","type":"article","venue":"Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228)","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Law of the iterated logarithm; Logarithm; Constant (computer programming); Iterated function; Iterated logarithm; Algorithm; Mathematics; Applied mathematics; Computer science; Mathematical analysis","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":[0.0003731591,0.0002690243,0.0004323625,0.00007277569,0.0003459443,0.0001774034,0.001402174,0.0001099331,0.00001657362],"category_scores_gemma":[0.0001707373,0.0001576481,0.0001950549,0.0004059644,0.0003407023,0.0002059925,0.0001940956,0.000179486,0.000009451783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002520536,"about_ca_system_score_gemma":0.00004175658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001553146,"about_ca_topic_score_gemma":0.000004598423,"domain_scores_codex":[0.9980864,0.00002227131,0.0005610628,0.0005179222,0.0004585092,0.0003538355],"domain_scores_gemma":[0.9976641,0.000350003,0.000490802,0.0004164344,0.0009452522,0.0001334243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000401087,0.0008700993,0.00009472082,0.00008769739,0.0001299112,9.842645e-7,0.0007098369,0.0005751498,0.08403872,0.5886941,0.003901842,0.3204958],"study_design_scores_gemma":[0.001743708,0.0003089121,0.0001356772,0.0002457748,0.0000364612,0.00001131622,0.00002895022,0.9758262,0.00273984,0.01829783,0.0004364004,0.0001889457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2653706,0.0001101509,0.7171068,0.009253174,0.001364973,0.003906492,0.000255546,0.0001595453,0.002472785],"genre_scores_gemma":[0.9782247,0.00005524299,0.01986386,0.00125375,0.0000885441,0.0001173643,4.889121e-7,0.00001565535,0.0003804044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.975251,"threshold_uncertainty_score":0.6428703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02821899487367748,"score_gpt":0.2444372383919912,"score_spread":0.2162182435183137,"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."}}