{"id":"W2970990876","doi":"","title":"Reducing the variance in online optimization by transporting past gradients","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of British Columbia","funders":"","keywords":"Hessian matrix; Estimator; Computer science; Iterated function; Variance (accounting); Variance reduction; Convergence (economics); Mathematical optimization; Rate of convergence; Optimization problem; Applied mathematics; Algorithm; Mathematics; Statistics; Mathematical analysis","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":[0.002706505,0.001671234,0.001672678,0.0007117154,0.0005982033,0.0014481,0.001812089,0.001832357,0.002327647],"category_scores_gemma":[0.01426906,0.001140417,0.0009802133,0.000759878,0.001533792,0.003061815,0.002240719,0.002922627,0.001228227],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009196741,"about_ca_system_score_gemma":0.001903931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003514217,"about_ca_topic_score_gemma":0.004648566,"domain_scores_codex":[0.9984908,0.0004784938,0.0001207692,0.0002650966,0.000517833,0.0001269318],"domain_scores_gemma":[0.996334,0.002082965,0.0002762894,0.000693775,0.0005091447,0.0001038422],"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":[0.0002610327,0.0001018172,0.001153069,0.0001991876,0.0001049879,0.0001485257,0.0001310167,0.8427143,0.01067447,0.02313019,0.003033279,0.1183481],"study_design_scores_gemma":[0.00001004601,0.0000288206,0.00008235052,0.000007781157,0.000007084919,0.00002074408,0.000003937373,0.991017,0.002402301,0.005899983,0.0005133883,0.000006509982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01125111,0.0002618504,0.9860013,0.0002230897,0.00005120802,0.00002394642,0.00003998588,0.001384796,0.0007626902],"genre_scores_gemma":[0.4391492,0.000571636,0.552631,0.0004005374,0.0001707066,0.0002527612,0.0004102508,0.001538436,0.004875516],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003514217,"threshold_uncertainty_score":0.01431352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01102596373962549,"score_gpt":0.2322976399575386,"score_spread":0.2212716762179131,"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."}}