{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008072717,0.001554709,0.001293973,0.001771403,0.0007614151,0.001935019,0.002475989,0.001794941,0.004629002],"category_scores_gemma":[0.06520455,0.001115624,0.001064919,0.001190906,0.00469608,0.005876866,0.004367828,0.004771109,0.0008229548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002276879,"about_ca_system_score_gemma":0.001671345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003644075,"about_ca_topic_score_gemma":0.002851981,"domain_scores_codex":[0.9978599,0.000904745,0.00008876265,0.0003364122,0.0006054551,0.0002046897],"domain_scores_gemma":[0.9652638,0.02827846,0.001679242,0.001923878,0.00227629,0.0005783038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001710426,0.00005638204,0.002293864,0.000425947,0.000109831,0.0001903098,0.000212932,0.4264033,0.002426266,0.5391241,0.004418803,0.02416729],"study_design_scores_gemma":[0.00001151466,0.00002282729,0.0004829564,0.00007378431,0.00001387355,0.00005185135,0.00003110436,0.7767904,0.0006082145,0.2210066,0.000888339,0.0000185678],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01832183,0.001570315,0.971512,0.00163793,0.0001009428,0.00003524675,0.000232176,0.00044726,0.00614227],"genre_scores_gemma":[0.7886316,0.005806055,0.1872212,0.001294336,0.0008687975,0.0006313605,0.001294254,0.0007998845,0.01345264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008072717,"threshold_uncertainty_score":0.04269314,"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."}}