{"id":"W3131097734","doi":"10.1007/s10994-022-06265-x","title":"SVRG meets AdaGrad: painless variance reduction","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia; SAIT Polytechnic; Université de Montréal; Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Minification; Mathematics; Variance reduction; Constant (computer programming); Reduction (mathematics); Heuristic; Variance (accounting); Robustness (evolution); Regular polygon; Algorithm; Mathematical optimization; Computer science; Applied mathematics; Statistics; Geometry","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":[0.00135739,0.001259845,0.001179731,0.0006218718,0.0003626952,0.001179681,0.00138694,0.00199781,0.007197113],"category_scores_gemma":[0.005218066,0.0005750418,0.0006088144,0.0006720786,0.0009000988,0.001567393,0.002039294,0.003330327,0.004302539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000426176,"about_ca_system_score_gemma":0.001154306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001705426,"about_ca_topic_score_gemma":0.002415158,"domain_scores_codex":[0.9989831,0.0003096997,0.00003631143,0.0001662782,0.0004288252,0.00007574774],"domain_scores_gemma":[0.9990804,0.0003769964,0.00005468351,0.0002312805,0.0001876268,0.00006903815],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003501147,0.0002706061,0.0004892026,0.0002081799,0.00006532337,0.0001484552,0.00007684323,0.1934165,0.0155439,0.07968695,0.03725536,0.6724886],"study_design_scores_gemma":[0.0000152363,0.00003753858,0.0000618326,0.00001047884,0.000004407472,0.00004552098,0.000006319074,0.975159,0.003581808,0.0171541,0.003916322,0.000007465882],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002757183,0.000157504,0.9921563,0.0003246175,0.0001830379,0.00002889992,0.00007602585,0.002079921,0.002236581],"genre_scores_gemma":[0.132837,0.0002974074,0.8473138,0.000438531,0.0002643733,0.0001508374,0.0005092677,0.00129273,0.01689605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007197113,"threshold_uncertainty_score":0.02407676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009090252797299359,"score_gpt":0.2034008846617872,"score_spread":0.1943106318644879,"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."}}