{"id":"W4392404184","doi":"10.23952/jano.6.2024.1.01","title":"Accelerated Bregman divergence optimization with SMART: An information geometric point of view","year":2024,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft","keywords":"Bregman divergence; Divergence (linguistics); Point (geometry); Kullback–Leibler divergence; Mathematics; Computer science; Optimization problem; Artificial intelligence; Mathematical optimization; Applied mathematics; Geometry; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.0003762814,0.0001262103,0.0003143711,0.0002592025,0.00005416727,0.00006970515,0.00007583389,0.00006322385,0.00007912304],"category_scores_gemma":[0.0001496227,0.00008759457,0.00003376865,0.0006665715,0.00004273233,0.0008647923,0.0000217431,0.0001487576,6.233998e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003107424,"about_ca_system_score_gemma":0.00004603058,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002227124,"about_ca_topic_score_gemma":8.577478e-8,"domain_scores_codex":[0.9988393,0.00003950459,0.0006098306,0.0001086718,0.0002857556,0.0001169606],"domain_scores_gemma":[0.9988756,0.0002433521,0.000379656,0.00008535536,0.0003007637,0.0001152415],"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":[0.0002273041,0.00008333333,0.000008278109,0.0002060893,0.00004346546,0.000003155844,0.0003385143,0.9108486,0.00006397774,0.02819072,0.0000584341,0.0599282],"study_design_scores_gemma":[0.0004842534,0.0005559942,0.00004062296,0.0001333722,0.0001256991,0.00003558384,0.0001082511,0.9777679,0.0004048489,0.02000098,0.0001924941,0.0001499471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001180003,0.0001079242,0.9978724,0.00007540957,0.0000705975,0.0001665705,0.000008972572,0.00002491501,0.0004932727],"genre_scores_gemma":[0.2113748,0.0003219932,0.7881902,0.00004790176,0.00003000904,0.000003725443,0.00001326233,0.00001327276,0.000004777924],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2101948,"threshold_uncertainty_score":0.3572003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04291470339763875,"score_gpt":0.3368643906240437,"score_spread":0.2939496872264049,"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."}}