{"id":"W3037273417","doi":"","title":"An Empirical Study of Stochastic Gradient Descent with Structured Covariance Noise","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Target Tracking and Data Fusion in Sensor Networks","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Covariance; Computer science; Stochastic gradient descent; Noise (video); Mathematics; Artificial intelligence; Statistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01157494,0.001031109,0.001405502,0.001516982,0.0007544308,0.001796663,0.002845126,0.002316109,0.003630437],"category_scores_gemma":[0.09702546,0.001042913,0.0009586452,0.001525474,0.003327948,0.005023561,0.001992591,0.002698189,0.0002505281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001420317,"about_ca_system_score_gemma":0.001928835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006886044,"about_ca_topic_score_gemma":0.005110152,"domain_scores_codex":[0.9975271,0.00155744,0.00009482951,0.0002914518,0.0003740235,0.00015527],"domain_scores_gemma":[0.9160459,0.07383517,0.002908594,0.00267658,0.003630569,0.0009031068],"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":[0.0002694834,0.0002913285,0.01558028,0.0004440994,0.0002308819,0.0004245761,0.0004859575,0.5649873,0.001713425,0.380117,0.005020155,0.03043555],"study_design_scores_gemma":[0.00001838055,0.00004952027,0.001932341,0.00005113574,0.00001704334,0.00009183487,0.00006088536,0.9671764,0.0001881526,0.02960744,0.0007883412,0.00001845159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2440673,0.004856339,0.7394854,0.003080414,0.0002312544,0.0001424758,0.0002223318,0.0003051302,0.007609454],"genre_scores_gemma":[0.9293525,0.001647205,0.06202164,0.0003313115,0.0003109737,0.0001253584,0.0005365268,0.0003561107,0.005318401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01157494,"threshold_uncertainty_score":0.06121486,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1220083634845631,"score_gpt":0.3505932410490974,"score_spread":0.2285848775645344,"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."}}