{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002982135,0.0001327937,0.0001681831,0.00008617154,0.0003242699,0.0003830303,0.0001227522,0.00005845055,0.00002595798],"category_scores_gemma":[0.0005906086,0.00009456668,0.00001722851,0.0003049624,0.0001003419,0.001390571,0.00002286021,0.0001335461,0.00009168248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003139305,"about_ca_system_score_gemma":0.00006132924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002812526,"about_ca_topic_score_gemma":0.000001933103,"domain_scores_codex":[0.9988866,0.00003988691,0.0004543072,0.0001089061,0.0002883305,0.000221994],"domain_scores_gemma":[0.9986137,0.0001934529,0.0002801958,0.000164492,0.0006700294,0.0000781608],"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":[0.0009379016,0.0003089599,0.01397526,0.009428112,0.000195378,0.0000141475,0.03624362,0.02893709,0.003174342,0.4887971,0.01400433,0.4039837],"study_design_scores_gemma":[0.001335776,0.001187107,0.004618718,0.001455719,0.0001118517,0.0003989548,0.004968274,0.9552128,0.001151751,0.006085531,0.02241039,0.001063183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3337268,0.00001042289,0.6604428,0.00004536288,0.0001825437,0.0001893943,0.000008469693,0.0001898139,0.005204454],"genre_scores_gemma":[0.9260402,2.762188e-7,0.07350537,0.0001173521,0.0001320875,0.00004311656,0.000004723044,0.000009793221,0.0001470912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9262757,"threshold_uncertainty_score":0.3856317,"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."}}