{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01018314,0.002149267,0.001954277,0.001854222,0.0007561784,0.001811189,0.003236569,0.002893368,0.00255969],"category_scores_gemma":[0.03633792,0.001317468,0.001247348,0.0008957807,0.002965598,0.003571798,0.004496584,0.003422198,0.0009525887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002356217,"about_ca_system_score_gemma":0.002243287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004896789,"about_ca_topic_score_gemma":0.004991476,"domain_scores_codex":[0.9969527,0.001518282,0.0001746152,0.0004275175,0.0007732717,0.0001536246],"domain_scores_gemma":[0.9876769,0.008433718,0.0007726018,0.001578209,0.001142304,0.0003963492],"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":[0.0001361935,0.00006555072,0.001556586,0.00008314681,0.00007731324,0.00005415726,0.00006503888,0.9307723,0.001877578,0.02195151,0.001013471,0.04234715],"study_design_scores_gemma":[0.000004128379,0.0000204498,0.00004759235,0.000006426474,0.000002406226,0.00001104706,0.000003585078,0.9934729,0.0005301055,0.005767859,0.0001284784,0.000005113654],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009616638,0.000130803,0.9888243,0.0001429365,0.00002362578,0.00003202457,0.00003853363,0.0005712544,0.0006198384],"genre_scores_gemma":[0.4605633,0.0002973338,0.5340109,0.000430449,0.00009854039,0.0003924169,0.0006745735,0.000806965,0.002725533],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01018314,"threshold_uncertainty_score":0.05385423,"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."}}