{"id":"W2995128076","doi":"","title":"A Closer Look at the Optimization Landscapes of Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Concatenation (mathematics); Computer science; Adversarial system; Generative grammar; Generator (circuit theory); Saddle point; Point (geometry); Visualization; Artificial intelligence; Field (mathematics); Deep learning; Bridge (graph theory); Machine learning; Theoretical computer science; Mathematical optimization; Mathematics","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":[0.0001370555,0.000121287,0.0001318915,0.00005041752,0.0002454492,0.0001600866,0.0005994256,0.00004552475,0.0008141882],"category_scores_gemma":[0.0003307843,0.00009321832,0.00008820007,0.0002349506,0.0000715011,0.0003208533,0.0002485867,0.0002054201,0.0000352406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003100003,"about_ca_system_score_gemma":0.00006081971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003597077,"about_ca_topic_score_gemma":0.0000176957,"domain_scores_codex":[0.998686,0.0002405477,0.000255813,0.0003418521,0.0003434852,0.0001323661],"domain_scores_gemma":[0.9988963,0.0002664365,0.0002240461,0.0002009581,0.0003489933,0.00006326377],"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":[0.00004106197,0.00002048546,0.0007638909,9.564237e-7,0.00006613704,0.000002320475,0.001441893,0.9757748,0.000672345,0.01755337,0.001803296,0.001859399],"study_design_scores_gemma":[0.0003160431,0.00008367646,0.0004682032,0.00001118356,0.00001066133,0.000001647415,0.0002360586,0.9957632,0.001399403,0.0001885319,0.001425426,0.00009594798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002092613,0.0000257156,0.9653345,0.01832916,0.0004033906,0.0001578575,0.000006985263,0.00005306766,0.01359665],"genre_scores_gemma":[0.98882,0.00007021487,0.009157435,0.0005675043,0.0003750098,0.00003532034,0.00005349475,0.000008395968,0.0009125831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9867274,"threshold_uncertainty_score":0.891479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0342901584745485,"score_gpt":0.28078537204376,"score_spread":0.2464952135692115,"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."}}