{"id":"W4384817809","doi":"10.1007/s11222-023-10274-8","title":"Generalized linear models for massive data via doubly-sketching","year":2023,"lang":"en","type":"article","venue":"Statistics and Computing","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generalized linear model; Computer science; Computation; Sequence (biology); Mathematical optimization; Linear model; Generalized linear mixed model; Least-squares function approximation; Algorithm; Poisson distribution; Data mining; Mathematics; Machine learning; Statistics; Estimator","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":[0.004608881,0.002331656,0.003207283,0.001310855,0.0008556565,0.00241102,0.004136032,0.002839743,0.005848203],"category_scores_gemma":[0.03324398,0.002142792,0.001690571,0.002154879,0.003101979,0.005540083,0.004774305,0.006361828,0.002006737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001346813,"about_ca_system_score_gemma":0.002180054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006512603,"about_ca_topic_score_gemma":0.008721128,"domain_scores_codex":[0.9971728,0.001546931,0.0001404984,0.0004123492,0.0005525138,0.0001748498],"domain_scores_gemma":[0.9742157,0.02024019,0.0009495079,0.003077459,0.0009693399,0.0005477463],"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":[0.0001425816,0.00007912689,0.0005368368,0.0002223435,0.0001026114,0.0001541076,0.0001273291,0.7887481,0.0008703912,0.1620096,0.004478551,0.04252839],"study_design_scores_gemma":[0.000009181474,0.00000886034,0.00003349056,0.000009817758,0.000005126964,0.00001111198,0.000005731336,0.9301445,0.0001021174,0.06926962,0.0003909076,0.000009452737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002338968,0.0002618536,0.9963822,0.0002213657,0.00003012857,0.00002180608,0.0001423576,0.0002789146,0.0003223522],"genre_scores_gemma":[0.3341241,0.002219769,0.6478217,0.0006793675,0.0006284476,0.0007999402,0.002229616,0.0006619265,0.01083513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006512603,"threshold_uncertainty_score":0.02437443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06817895037337768,"score_gpt":0.3234575491311318,"score_spread":0.2552785987577542,"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."}}