{"id":"W3094191864","doi":"","title":"Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial neural network; Sampling (signal processing); Function (biology); Artificial intelligence; Training set; Goodness of fit; Energy (signal processing); Feature (linguistics); Data modeling; Machine learning; Algorithm; Mathematics; 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":[0.0005813929,0.000194163,0.000197806,0.00005899052,0.0004873062,0.0004924513,0.0005680693,0.00004084672,0.00003163981],"category_scores_gemma":[0.0006461898,0.0001480191,0.00008175422,0.0001144535,0.00004591066,0.0003616203,0.0001630381,0.000393723,0.000002393877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002369067,"about_ca_system_score_gemma":0.00008889322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005542408,"about_ca_topic_score_gemma":0.00001090725,"domain_scores_codex":[0.9983894,0.0002646779,0.0002523707,0.000485983,0.0003680173,0.0002396016],"domain_scores_gemma":[0.9988747,0.0005066966,0.0002036074,0.0001245889,0.0002001448,0.00009031175],"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":[0.00005697136,0.00001026115,0.0004337061,0.000006426517,0.00004549858,0.000001268869,0.00287167,0.668367,0.002292789,0.1266963,0.000006009805,0.1992121],"study_design_scores_gemma":[0.0004910691,0.0003395466,0.00005545532,0.00006420003,0.00001065231,0.000001677531,0.0003209356,0.990494,0.000284058,0.005648018,0.002111867,0.0001785075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005736857,0.00006905381,0.9806064,0.011281,0.0001406595,0.000132702,0.000004019802,0.0001126676,0.001916676],"genre_scores_gemma":[0.9164335,0.00001556422,0.08196206,0.00108803,0.0002455908,0.00003984381,0.00002006741,0.00001798696,0.0001773503],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9106966,"threshold_uncertainty_score":0.6036042,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1657884621947862,"score_gpt":0.3439734482612751,"score_spread":0.1781849860664889,"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."}}