{"id":"W2889576094","doi":"","title":"Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization.","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mathematics; Variance reduction; Gradient descent; Combinatorics; Nabla symbol; Stationary point; Function (biology); Stochastic gradient descent; Applied mathematics; Mathematical analysis; Computer science; Physics; Statistics; Omega","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":[0.0003709342,0.0002352642,0.0002373253,0.0003205022,0.0004947213,0.000979458,0.0006885989,0.000108488,0.000004415297],"category_scores_gemma":[0.0002570219,0.0002210834,0.00005429094,0.0008300742,0.00009180659,0.004002894,0.00008882546,0.00009370263,0.00002295079],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535031,"about_ca_system_score_gemma":0.0001620872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001076733,"about_ca_topic_score_gemma":3.278502e-7,"domain_scores_codex":[0.9980615,0.0000441304,0.0008001485,0.0003009095,0.0004053446,0.0003879367],"domain_scores_gemma":[0.9973581,0.00007121187,0.0006432846,0.0004220182,0.001369808,0.0001355901],"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":[0.00004590099,0.00006301144,0.00001472189,0.000381942,0.00001885456,5.314538e-7,0.004302114,0.9316582,0.0001425887,0.04111437,0.002771439,0.01948634],"study_design_scores_gemma":[0.0004851334,0.0002013199,0.00002544153,0.0001614027,0.000009879445,0.00005136108,0.00008383003,0.9976058,0.000356826,0.0001957928,0.0005703549,0.0002528811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000326094,0.00005515337,0.9949181,0.0003720227,0.00169708,0.001303788,0.000007898361,0.0009371894,0.000382695],"genre_scores_gemma":[0.7961357,0.00000129975,0.2025311,0.000469617,0.0002290507,0.0004639179,0.00005106004,0.00001896998,0.00009930479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7958096,"threshold_uncertainty_score":0.9444937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02298046378812457,"score_gpt":0.2619998012515888,"score_spread":0.2390193374634642,"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."}}