{"id":"W2115684092","doi":"10.1109/cdc.2001.981010","title":"Law of the iterated logarithm for a constant-gain linear stochastic gradient algorithm","year":2003,"lang":"en","type":"article","venue":"Proceedings of the 40th IEEE Conference on Decision and Control (Cat. No.01CH37228)","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Law of the iterated logarithm; Logarithm; Constant (computer programming); Iterated logarithm; Iterated function; Mathematics; Applied mathematics; Limiting; Zero (linguistics); Natural logarithm; Stochastic process; Algorithm; Mathematical analysis; Computer science; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00184011,0.0004007842,0.0008346863,0.0001101836,0.0002720736,0.00009091073,0.0006334839,0.0002139064,0.00002307422],"category_scores_gemma":[0.003423057,0.0002318949,0.0003431489,0.0002614263,0.0004362959,0.0001020647,0.0000933903,0.0002389738,3.925774e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005074504,"about_ca_system_score_gemma":0.0001476807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001680562,"about_ca_topic_score_gemma":0.00001191331,"domain_scores_codex":[0.997526,0.00009317905,0.0008622393,0.0005009054,0.000581896,0.000435795],"domain_scores_gemma":[0.995823,0.001167375,0.0007732767,0.0004081407,0.001663574,0.0001646307],"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":[0.00185372,0.0008274664,0.0001093731,0.000423577,0.0002819482,0.000001277238,0.001082632,0.00002906256,0.1077618,0.8386451,0.001473804,0.0475102],"study_design_scores_gemma":[0.01406697,0.001679215,0.00008543787,0.00225362,0.0006020932,0.00005711578,0.001288313,0.6993204,0.04233335,0.2355785,0.001778631,0.0009564026],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6735899,0.00008692945,0.3078623,0.001055529,0.001910209,0.004915805,0.0005000526,0.00009941224,0.009979875],"genre_scores_gemma":[0.8983001,0.00004502551,0.09963188,0.0006985982,0.00008324559,0.0001388148,8.636285e-7,0.00005066236,0.001050841],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6992913,"threshold_uncertainty_score":0.94564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05293776873898644,"score_gpt":0.3145715270823066,"score_spread":0.2616337583433201,"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."}}