{"id":"W3094116343","doi":"10.1007/s10994-023-06337-6","title":"The role of mutual information in variational classifiers","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"H2020 Marie Skłodowska-Curie Actions; Universidad de Buenos Aires; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Information bottleneck method; Mutual information; Overfitting; Artificial intelligence; Regularization (linguistics); Computer science; Mathematics; Generalization; Kullback–Leibler divergence; Early stopping; MNIST database; Entropy (arrow of time); Inference; Algorithm; Machine learning; Artificial neural network","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":[0.0008419888,0.0000562891,0.00006596396,0.0001773973,0.0001928151,0.0001044654,0.0002944443,0.0000298091,0.00001428696],"category_scores_gemma":[0.000408728,0.00004535992,0.00002763378,0.0006881428,0.0000223567,0.0004794423,0.0001117614,0.0002213308,0.0001372189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002257102,"about_ca_system_score_gemma":0.00004289134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004646006,"about_ca_topic_score_gemma":0.00001531855,"domain_scores_codex":[0.99914,0.0001280613,0.0002265675,0.00008482071,0.000258746,0.000161839],"domain_scores_gemma":[0.999383,0.0003097127,0.0001253442,0.0001169979,0.00003807788,0.00002681197],"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":[0.00001627904,0.00001046739,0.04952139,0.000006768201,0.00001160511,0.000001802581,0.009096131,0.2154004,0.0004286346,0.3123102,0.0001350531,0.4130613],"study_design_scores_gemma":[0.0001804041,0.00001858236,0.03926004,0.000004666595,5.597479e-7,0.000001119164,0.0005209335,0.8607024,0.0000265836,0.00225384,0.09698454,0.00004633272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1340718,0.0003236747,0.76965,0.006768359,0.000915891,0.0004585554,0.000004299479,0.001072486,0.08673488],"genre_scores_gemma":[0.996949,0.00001448187,0.00245335,0.00007499794,0.00001712832,0.000007448058,0.00001821663,0.000003634633,0.0004617007],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8628772,"threshold_uncertainty_score":0.1849724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00828382254537237,"score_gpt":0.2255312153029866,"score_spread":0.2172473927576142,"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."}}