{"id":"W3011675874","doi":"10.1109/tsp.2020.2979601","title":"Subsampling Generative Adversarial Networks: Density Ratio Estimation in Feature Space With Softplus Loss","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Signal Processing","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Discriminator; MNIST database; Computer science; Artificial intelligence; Feature (linguistics); Pattern recognition (psychology); Convergence (economics); Generative grammar; Generative adversarial network; Sample (material); Density ratio; Algorithm; Deep learning; Telecommunications; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001839599,0.0002842734,0.000291408,0.0001052987,0.0004884743,0.0003853565,0.000301671,0.0001236743,0.00001446623],"category_scores_gemma":[0.000008369432,0.0002508859,0.00007168182,0.0009691852,0.00007861963,0.001304585,0.000004882207,0.0005025939,0.000007828148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001013697,"about_ca_system_score_gemma":0.0002059274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002365839,"about_ca_topic_score_gemma":0.00008992055,"domain_scores_codex":[0.9983038,0.0001457799,0.0002427456,0.0006213943,0.0003348351,0.0003514132],"domain_scores_gemma":[0.9992509,0.0001207325,0.0001414622,0.0001699336,0.0001640638,0.000152932],"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":[0.0001764186,0.00004989561,0.00002022187,0.00001483659,0.00002298316,0.0000304591,0.001419293,0.9473442,0.001204603,0.00006878525,0.00004327729,0.04960507],"study_design_scores_gemma":[0.000700521,0.0001735776,0.00005307397,0.00009926127,0.00002659546,0.0000117362,0.00009391463,0.9601005,0.03834363,0.00007695371,0.00003081114,0.0002894563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001620314,0.00009958772,0.9949815,0.002646929,0.0001667402,0.0002763802,0.000002549335,0.0001504086,0.00005556272],"genre_scores_gemma":[0.8680502,0.000007770414,0.1310711,0.0006117488,0.0001909834,0.00001973626,0.000002341002,0.0000199123,0.00002613563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8664299,"threshold_uncertainty_score":0.9999943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01689495322428257,"score_gpt":0.2284269665349876,"score_spread":0.211532013310705,"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."}}