{"id":"W2963436208","doi":"","title":"Optimal Subsampling with Influence Functions","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Asymptotically optimal algorithm; Estimator; Probabilistic logic; Computer science; Mathematical optimization; Function (biology); Class (philosophy); Statistical model; Importance sampling; Applied mathematics; Mathematics; Algorithm; Statistics; Artificial intelligence; 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":[0.009838575,0.001777162,0.002504925,0.002292565,0.001030303,0.002030421,0.002133644,0.001820045,0.00288968],"category_scores_gemma":[0.05641501,0.001130538,0.001975637,0.001730003,0.002311405,0.002877037,0.00239044,0.002459661,0.0006615461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001864311,"about_ca_system_score_gemma":0.002305033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006900018,"about_ca_topic_score_gemma":0.00700985,"domain_scores_codex":[0.9927556,0.00431578,0.0003318739,0.0009853553,0.001321496,0.0002900057],"domain_scores_gemma":[0.9746694,0.02037918,0.001035576,0.002378265,0.001181422,0.0003562052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000518047,0.0001877718,0.004317075,0.0005364239,0.0004372848,0.0003396214,0.0004417081,0.5440528,0.004473025,0.2434677,0.005017166,0.1962113],"study_design_scores_gemma":[0.00002853381,0.00005063291,0.00038868,0.00004569075,0.00005491687,0.00006757797,0.00002807239,0.9260973,0.002272577,0.0688639,0.002079988,0.00002225348],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003387804,0.0002800459,0.9953903,0.000104003,0.00003351737,0.00006205998,0.00003952251,0.0001992796,0.0005034885],"genre_scores_gemma":[0.265685,0.001025155,0.7282324,0.0005014238,0.0003627893,0.0006873038,0.0007670115,0.0004487833,0.002290108],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009838575,"threshold_uncertainty_score":0.05203199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07281130759508428,"score_gpt":0.3516244162452848,"score_spread":0.2788131086502005,"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."}}