{"id":"W1975973957","doi":"10.1007/s10107-007-0145-1","title":"How does a stochastic optimization/approximation algorithm adapt to a randomly evolving optimum/root with jump Markov sample paths","year":2007,"lang":"en","type":"article","venue":"Mathematical Programming","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Jump; Sample (material); Markov chain; Algorithm; Root (linguistics); Mathematical optimization; Stochastic approximation; Jump process; 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":[0.0007307954,0.0002708528,0.0003255638,0.0001424011,0.0003325181,0.0009487471,0.0005783821,0.00007672114,0.00001852107],"category_scores_gemma":[0.0002689863,0.0001823045,0.00008465051,0.0009440879,0.00006658058,0.0005600345,0.0002096592,0.000188319,0.00001355943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000640299,"about_ca_system_score_gemma":0.00003877103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008016298,"about_ca_topic_score_gemma":0.00001553287,"domain_scores_codex":[0.9978344,0.00003890257,0.0004048629,0.0005569493,0.0005255914,0.0006392723],"domain_scores_gemma":[0.9980094,0.0007458536,0.0001597411,0.0005715417,0.0002038029,0.000309614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005484528,0.0005340084,0.0000133134,0.0001583066,0.00006230407,0.00002604791,0.00150134,0.04078186,0.00008825101,0.06876507,0.0002983273,0.8877164],"study_design_scores_gemma":[0.0006542045,0.0001427521,0.0000132589,0.0001472116,0.00002624803,0.00003436787,0.0001560856,0.9869557,0.0001108121,0.01084312,0.00058273,0.0003335351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002224585,0.00003228071,0.994612,0.003016899,0.0000585836,0.001478752,0.00000314843,0.0003889905,0.0001868221],"genre_scores_gemma":[0.1112533,5.399186e-7,0.888027,0.00009411013,0.0001165984,0.0003238558,0.000007926973,0.00002917773,0.0001475887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9461738,"threshold_uncertainty_score":0.914879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.011375396128301,"score_gpt":0.2388547975618677,"score_spread":0.2274794014335667,"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."}}