{"id":"W3166610402","doi":"10.48550/arxiv.2102.08431","title":"Complex Momentum for Optimization in Games","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Momentum (technical analysis); Differentiable function; Convergence (economics); Bilinear interpolation; Generative grammar; Generalization; Adversarial system; Computer science; Mathematical optimization; Perspective (graphical); Gradient descent; Applied mathematics; Mathematics; Algorithm; Artificial intelligence; Pure mathematics; Artificial neural network; Mathematical analysis; Economics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001677379,0.0002138466,0.0003020157,0.0001813626,0.00009043059,0.0001941801,0.000842447,0.0001551718,0.00004713247],"category_scores_gemma":[0.00003843244,0.0002593029,0.000167047,0.0004428588,0.00004388826,0.0003725874,0.000968899,0.000187402,0.0000035464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151454,"about_ca_system_score_gemma":0.0001362427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009584042,"about_ca_topic_score_gemma":0.00007060371,"domain_scores_codex":[0.9985012,0.0001360062,0.0001744236,0.000861018,0.00005373843,0.0002736483],"domain_scores_gemma":[0.9988737,0.00009863042,0.0001498021,0.0006302189,0.0001731497,0.00007448862],"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":[0.000009240824,0.00005917572,0.0002113781,0.00002734605,0.00003369927,0.00003933551,0.0001362327,0.9914561,0.00004003307,0.007099536,0.0004114107,0.0004765329],"study_design_scores_gemma":[0.0004035415,0.00002292878,0.0003829777,0.00005229902,0.00002063189,5.840179e-7,0.00009930236,0.9951375,0.0001658305,0.002994679,0.0004523413,0.0002673674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006270619,0.0000678115,0.991886,0.0002126535,0.0004795483,0.0003515282,0.0000101978,0.00006407762,0.0006575359],"genre_scores_gemma":[0.930801,0.0001654351,0.06830111,0.00009467915,0.00007462377,0.000003222183,0.00006213054,0.00001201065,0.0004857471],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9245304,"threshold_uncertainty_score":0.9999859,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08543563773179376,"score_gpt":0.1957959397475408,"score_spread":0.110360302015747,"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."}}