{"id":"W1807715286","doi":"10.48550/arxiv.1304.5586","title":"Tail bounds for stochastic approximation","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stochastic approximation; Variance (accounting); Convergence (economics); Convex function; Mathematical optimization; Rate of convergence; Computer science; Scale (ratio); Regular polygon; Applied mathematics; Mathematics; Key (lock)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00005513044,0.0002474675,0.0002417466,0.0001630303,0.00007069188,0.00006946429,0.0003201083,0.0002780785,0.00002592766],"category_scores_gemma":[0.00001581655,0.0003054254,0.0001298635,0.0001138681,0.00004790082,0.0001192397,0.000180787,0.0002860169,0.00004153352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001484483,"about_ca_system_score_gemma":0.00002788426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003301921,"about_ca_topic_score_gemma":0.000007049749,"domain_scores_codex":[0.9992056,0.00001676112,0.0001286177,0.0003723562,0.00003876464,0.0002378973],"domain_scores_gemma":[0.9991995,0.00005153444,0.0000711407,0.0004911552,0.0001193183,0.00006738588],"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":[0.00001147894,0.00001793302,0.00001930005,0.0001090055,0.00009336766,0.00000717781,0.00006246783,0.9758312,0.000331016,0.01791251,0.004988188,0.0006163403],"study_design_scores_gemma":[0.0001813685,0.00001983079,0.00004362877,0.000110259,0.00008228442,0.000001261169,0.00002872735,0.9215464,0.0008404708,0.07627849,0.0005352367,0.0003320577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2384825,0.00006416415,0.7577709,0.000008497212,0.000388191,0.000492601,0.00001764859,0.0009797047,0.001795781],"genre_scores_gemma":[0.9971017,0.00003884374,0.002033076,0.00001688803,0.0001166594,0.000008030417,0.00006243028,0.00004903496,0.000573332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7586192,"threshold_uncertainty_score":0.9999398,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06673869972299941,"score_gpt":0.1779139716390434,"score_spread":0.111175271916044,"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."}}