{"id":"W2948930516","doi":"10.48550/arxiv.1906.03532","title":"Reducing the variance in online optimization by transporting past gradients","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of British Columbia","funders":"","keywords":"Variance (accounting); Computer science; Econometrics; Environmental science; Statistics; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002904693,0.001558928,0.001744763,0.0007883504,0.0006070139,0.001554052,0.001742027,0.001855727,0.002176438],"category_scores_gemma":[0.01494165,0.001168918,0.0009834639,0.0008027373,0.00167922,0.003087407,0.002228915,0.002934447,0.00116799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009714753,"about_ca_system_score_gemma":0.001929988,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003450528,"about_ca_topic_score_gemma":0.004094839,"domain_scores_codex":[0.9982011,0.0005557179,0.0001353487,0.0003027376,0.0006636765,0.0001414854],"domain_scores_gemma":[0.9955687,0.002524874,0.0003459196,0.0008444725,0.0005914345,0.0001245923],"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":[0.0002585,0.0001112723,0.00137959,0.0002137469,0.0001048786,0.0001635918,0.0001357883,0.8472672,0.01067199,0.02679361,0.002983051,0.1099168],"study_design_scores_gemma":[0.000009710121,0.00002666925,0.00008630198,0.000007578343,0.000007043799,0.00002039472,0.000003880899,0.9902635,0.002039669,0.007044206,0.0004850227,0.000005946143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01343232,0.0002867636,0.9837527,0.0002531605,0.00005213402,0.00002498047,0.00004100891,0.001320411,0.0008365298],"genre_scores_gemma":[0.4847686,0.0006373753,0.5062945,0.0003885688,0.0002012022,0.0002486415,0.0004361223,0.001597642,0.005427306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003450528,"threshold_uncertainty_score":0.01536167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04322426133291139,"score_gpt":0.190104723853462,"score_spread":0.1468804625205506,"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."}}