{"id":"W2970271714","doi":"","title":"A Latent Variational Framework for Stochastic Optimization","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Stochastic optimization; Stochastic gradient descent; Stochastic differential equation; Mathematical optimization; Computer science; Gradient descent; Continuous-time stochastic process; Inference; Stochastic process; Optimization problem; Stochastic approximation; Mathematics; Applied mathematics; Artificial intelligence; Key (lock); Artificial neural network","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":[0.0002767799,0.0001538299,0.000170812,0.0002489407,0.0001685731,0.0007990105,0.0004312766,0.0001167,0.00001024551],"category_scores_gemma":[0.00019521,0.000144584,0.0000478117,0.0004702486,0.00001427075,0.003843068,0.00006058457,0.0001019188,0.00004187481],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009113903,"about_ca_system_score_gemma":0.0000981482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003839809,"about_ca_topic_score_gemma":3.113591e-8,"domain_scores_codex":[0.9986007,0.00002493911,0.0005449345,0.0001997498,0.000398493,0.0002311914],"domain_scores_gemma":[0.9984705,0.0001390155,0.0004789427,0.00027393,0.0005731543,0.0000644556],"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":[0.000006182649,0.000008781175,0.00002027661,0.0001033974,0.000003994784,3.156055e-8,0.0004436711,0.7920122,0.000003343686,0.2051502,0.00008855006,0.002159343],"study_design_scores_gemma":[0.0002890826,0.00007756399,0.00003563812,0.0001238615,0.000004999492,0.0000153027,0.00003072679,0.9961075,0.00001497769,0.002981613,0.0001498011,0.0001689175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000123144,0.00003957573,0.9963022,0.0003389303,0.001157035,0.001166994,0.000008174342,0.0006075506,0.0002564114],"genre_scores_gemma":[0.5087524,6.742993e-7,0.4903635,0.0003576459,0.00007285744,0.0002901283,0.00007439361,0.00001136999,0.00007702309],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5086293,"threshold_uncertainty_score":0.7704877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01698382096749571,"score_gpt":0.2520262587933482,"score_spread":0.2350424378258525,"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."}}