{"id":"W2962705652","doi":"","title":"Stop wasting my gradients: practical SVRG","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Convergence (economics); Variance (accounting); Computation; Generalization; Rate of convergence; Selection (genetic algorithm); Mathematical optimization; Algorithm; Artificial intelligence; Applied mathematics; Mathematics; Channel (broadcasting)","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006100062,0.0001676214,0.0001760611,0.0002552771,0.0001934714,0.00115394,0.000469384,0.00008381435,0.000001284031],"category_scores_gemma":[0.0006864557,0.0001489771,0.00003129127,0.000660646,0.00004203045,0.008841286,0.0001475634,0.0001758286,0.00007374894],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001388423,"about_ca_system_score_gemma":0.0001890759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001566351,"about_ca_topic_score_gemma":1.504029e-7,"domain_scores_codex":[0.9981592,0.00006812799,0.0006315282,0.0001916249,0.00064577,0.0003037684],"domain_scores_gemma":[0.9982119,0.00005878915,0.0005000603,0.0003121405,0.0007154971,0.000201624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006956046,0.000311449,0.002837243,0.001675547,0.00005803497,0.00003725452,0.05330075,0.1468003,0.0001442708,0.5064913,0.05867814,0.2295962],"study_design_scores_gemma":[0.0003184941,0.00007770128,0.00003629442,0.0001110724,0.000004540357,0.0002226738,0.00064419,0.9930332,0.0001134675,0.0003524507,0.004895522,0.0001903843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001601855,0.00008462458,0.9902751,0.0006812838,0.00105101,0.0003439028,0.000001527997,0.001081457,0.004879282],"genre_scores_gemma":[0.9259959,0.000001468152,0.07315734,0.0004930396,0.0001119354,0.0000906589,0.00001872899,0.00001141229,0.0001195154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9243941,"threshold_uncertainty_score":0.9998829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06114805913386867,"score_gpt":0.3037481648630557,"score_spread":0.2426001057291871,"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."}}