{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003859148,0.0001182324,0.0001536475,0.0001108316,0.0002644932,0.0001580082,0.0006465206,0.00003452544,8.704828e-7],"category_scores_gemma":[0.0001082229,0.0001194024,0.00001523585,0.0002731816,0.00002855744,0.0001987972,0.0008775236,0.00006871303,0.000002697282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001247179,"about_ca_system_score_gemma":0.00003417406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002068245,"about_ca_topic_score_gemma":0.000001194889,"domain_scores_codex":[0.9988692,0.00002541312,0.0002408706,0.0004372728,0.0001604127,0.0002668401],"domain_scores_gemma":[0.9988467,0.0003781713,0.0001151636,0.0004694823,0.0001197319,0.0000707871],"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":[0.000004315863,0.00001165438,0.00001260156,0.00004731324,0.00002213718,0.000008309166,0.0006371757,0.106069,0.00008579069,0.8273006,0.004677494,0.06112365],"study_design_scores_gemma":[0.0002378946,0.00003107122,0.00001762331,0.00001663149,0.000006581943,0.000003341758,0.00001114431,0.8340071,0.00004181097,0.165406,0.00009885131,0.0001218677],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004633669,0.00003101931,0.9981181,0.0002025498,0.0002804674,0.0002544181,0.0001621972,0.0004307822,0.0000570854],"genre_scores_gemma":[0.08111451,0.00001667161,0.9183893,0.0001208277,0.00008085483,0.000008120736,0.0002163279,0.00001514489,0.00003830054],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7279382,"threshold_uncertainty_score":0.486909,"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."}}