{"id":"W2918348138","doi":"10.1109/isit.2019.8849316","title":"Asymptotics of MAP Inference in Deep Networks","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Naval Research; York University; National Science Foundation","keywords":"Inference; Computer science; Maximum a posteriori estimation; A priori and a posteriori; Prior probability; Limit (mathematics); Algorithm; Generative grammar; Artificial intelligence; Mathematics; Bayesian probability; Maximum likelihood; Statistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.00005456488,0.0001658094,0.0003007175,0.0001085315,0.000003263048,0.0000157085,0.0002320076,0.0003029645,0.00003375755],"category_scores_gemma":[0.00001271758,0.0001687137,0.00005455959,0.00005490849,0.00001697783,0.00001975925,0.0002843126,0.0004694687,0.000009735814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000339142,"about_ca_system_score_gemma":0.0000152105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000709018,"about_ca_topic_score_gemma":0.00005897182,"domain_scores_codex":[0.9993536,0.00001362699,0.0002475994,0.0001475269,0.00008345235,0.0001541745],"domain_scores_gemma":[0.9993579,0.00008136436,0.00004367008,0.000455135,0.00004138224,0.00002056737],"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":[0.000001338393,0.000007533755,0.001955737,0.00007394092,0.00001843654,0.000002551671,0.00003747988,0.9947016,0.00008071091,0.0005629157,0.0005533476,0.002004379],"study_design_scores_gemma":[0.00005135934,0.000008553031,0.001442354,0.0004027203,0.000007968399,2.962983e-7,0.000007691138,0.9914522,0.003557536,0.002670829,0.0002057191,0.0001928405],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04337509,0.001076065,0.92755,0.00001320094,0.001044574,0.0002952502,0.000002485122,0.000668272,0.02597508],"genre_scores_gemma":[0.9912909,0.0003283775,0.008212922,0.0000186781,0.00004599683,0.000004944971,0.00001141275,0.00002670047,0.00006009457],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9479158,"threshold_uncertainty_score":0.6879946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01472700621355297,"score_gpt":0.2396521619738337,"score_spread":0.2249251557602807,"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."}}