{"id":"W4322707172","doi":"10.1109/tit.2023.3250099","title":"Martingale Methods for Sequential Estimation of Convex Functionals and Divergences","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Markov Chains and Monte Carlo Methods","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Mathematics; Regular polygon; Martingale (probability theory); Applied mathematics; Convex function; Kullback–Leibler divergence; Logarithm; Probability measure; Combinatorics; Discrete mathematics; Mathematical optimization; Statistics; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002743013,0.0001061878,0.0001838596,0.000268098,0.0001871378,0.00002455991,0.00006394744,0.00008072669,0.00008843547],"category_scores_gemma":[0.00025308,0.00009643077,0.0001047468,0.0002308717,0.00007490612,0.0004601623,0.000001938181,0.00007786708,0.000001427369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000197435,"about_ca_system_score_gemma":0.00003011452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003130269,"about_ca_topic_score_gemma":9.212471e-7,"domain_scores_codex":[0.9989792,0.0002140119,0.0004469455,0.00008930791,0.0001406606,0.0001298708],"domain_scores_gemma":[0.9975563,0.001901834,0.0002102687,0.000141079,0.0001452631,0.00004522205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003830277,0.00005680682,0.000002765134,0.0007093475,0.0001735877,1.1732e-7,0.003984858,0.009963075,0.001737633,0.1436432,0.001659127,0.8376865],"study_design_scores_gemma":[0.001899337,0.0004308035,0.00004297408,0.0001519352,0.0003546235,0.00001201473,0.004347557,0.3773017,0.2041824,0.4032151,0.007577432,0.0004841225],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01005859,0.00001130161,0.9876017,0.00009137802,0.00068466,0.0003985586,0.0001078036,0.0001270963,0.0009188866],"genre_scores_gemma":[0.5317361,0.00007599041,0.4655074,0.000277824,0.000054116,0.0004352393,0.00005155277,0.00002667219,0.001835105],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8372024,"threshold_uncertainty_score":0.3932332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07514884128663901,"score_gpt":0.4022217221927577,"score_spread":0.3270728809061187,"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."}}