{"id":"W7105913978","doi":"10.23952/jano.7.2025.3.07","title":"Variable Bregman majorization-minimization algorithm and its application to Dirichlet maximum likelihood estimation","year":2025,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Mathematics Research Center MATH+; Deutsche Forschungsgemeinschaft","keywords":"Maximum likelihood; Variable (mathematics); Expectation–maximization algorithm; Estimation; Dirichlet distribution; Estimation theory; Maximum likelihood sequence estimation","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":[0.0003813777,0.0001441452,0.0002550241,0.0002728304,0.0001463199,0.0001588408,0.0002003362,0.0001042364,0.000003927707],"category_scores_gemma":[0.00005708716,0.0001306514,0.00002528931,0.0008557859,0.00001319177,0.0004541619,0.00009438912,0.000122515,0.000001264489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004186401,"about_ca_system_score_gemma":0.00007486126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001810038,"about_ca_topic_score_gemma":4.251845e-8,"domain_scores_codex":[0.9988595,0.00004790707,0.0004511884,0.0002729554,0.000208592,0.0001599034],"domain_scores_gemma":[0.9990798,0.00008444006,0.0002825007,0.0001479272,0.0002562062,0.0001491752],"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":[0.00003278931,0.00007258273,0.000007884701,0.00002953781,0.00002381815,7.341096e-7,0.0002099688,0.1677696,0.0006274508,0.1626088,0.000196475,0.6684203],"study_design_scores_gemma":[0.0004190289,0.00007696444,0.0001038901,0.00003051841,0.00003384177,0.00001192001,0.000007642636,0.9139967,0.0006146419,0.08394878,0.0006352238,0.0001208346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004299779,0.0001570812,0.9968855,0.001329039,0.0001478866,0.0002968707,0.00000175376,0.00003572063,0.001103105],"genre_scores_gemma":[0.02341238,0.0001058074,0.9756024,0.0007515149,0.0000648943,0.00001650048,0.000008749236,0.000009768556,0.00002791934],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7462271,"threshold_uncertainty_score":0.5327811,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00387340013188319,"score_gpt":0.2353775001156472,"score_spread":0.231504099983764,"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."}}