{"id":"W3103712156","doi":"10.48550/arxiv.2103.12243","title":"Adaptive Importance Sampling for Finite-Sum Optimization and Sampling with Decreasing Step-Sizes","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Regret; Variance reduction; Estimator; Sampling (signal processing); Mathematical optimization; Convergence (economics); Variance (accounting); Computer science; Importance sampling; Rate of convergence; Adaptive sampling; Mathematics; Algorithm; Key (lock); Statistics; Machine learning; Monte Carlo method","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":[0.005219918,0.001314344,0.001467262,0.0009282646,0.0006856341,0.00126074,0.001982839,0.00135256,0.00240636],"category_scores_gemma":[0.02657897,0.0007791753,0.0008855218,0.0009618867,0.001952941,0.002153694,0.002055841,0.00317769,0.0006343008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001680244,"about_ca_system_score_gemma":0.001896468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002449233,"about_ca_topic_score_gemma":0.003433425,"domain_scores_codex":[0.9967136,0.001681006,0.000136585,0.0004924511,0.0007788881,0.0001974406],"domain_scores_gemma":[0.9884544,0.008991815,0.0005195152,0.001072871,0.0006861363,0.0002753271],"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":[0.0003096724,0.0002179349,0.001524637,0.0002508239,0.0000876899,0.0001182632,0.0001189298,0.7350499,0.003846962,0.1615801,0.003418192,0.09347683],"study_design_scores_gemma":[0.00002336513,0.00002795088,0.00008119153,0.00000984074,0.000005145581,0.00001505539,0.000003805405,0.972481,0.0008784359,0.02608509,0.0003834779,0.000005704374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004373829,0.0001691552,0.9941526,0.0001797685,0.00003283937,0.00003754031,0.00002231949,0.0002257629,0.0008062225],"genre_scores_gemma":[0.3564909,0.0004562135,0.638489,0.000444552,0.0001860306,0.0004784024,0.0002394699,0.0002648836,0.002950634],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005219918,"threshold_uncertainty_score":0.02760589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09071579776244318,"score_gpt":0.2069464663268825,"score_spread":0.1162306685644394,"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."}}