{"id":"W3092700804","doi":"10.48550/arxiv.2010.09063","title":"Enabling Fast Differentially Private SGD via Just-in-Time Compilation and Vectorization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Compiler; Vectorization (mathematics); Programming language; Overhead (engineering); Parallel computing; Matching (statistics); Code (set theory); Graph; Theoretical computer science; Set (abstract data type)","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":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0001979768,0.0003198845,0.0003625489,0.0004039148,0.0001224054,0.000262971,0.01328426,0.0003648199,0.00001438738],"category_scores_gemma":[0.001049632,0.000397624,0.00006793301,0.0008634585,0.0001063797,0.0006786627,0.09385508,0.0007020019,0.00004232702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002349249,"about_ca_system_score_gemma":0.00007162378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004763119,"about_ca_topic_score_gemma":0.00001595448,"domain_scores_codex":[0.9977634,0.0001348983,0.0002622846,0.001355001,0.0001507944,0.0003336521],"domain_scores_gemma":[0.9955907,0.0001109176,0.0002944481,0.003821571,0.00007693199,0.0001053801],"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":[0.0005840876,0.001390563,0.3456325,0.002980428,0.001117748,0.003403897,0.002587645,0.188691,0.05300621,0.347528,0.01076432,0.04231359],"study_design_scores_gemma":[0.0003606766,0.00002920849,0.01229127,0.0001121869,0.00002701234,0.000002069708,0.000007420811,0.7999636,0.0006618015,0.1861102,0.00008669392,0.0003478285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2335575,0.00002740229,0.7638849,0.001055547,0.0003098981,0.000292486,0.00003477901,0.0006841901,0.0001532562],"genre_scores_gemma":[0.9817122,0.0001861211,0.01777594,0.00004776195,0.00005170739,0.000001021741,0.0001566872,0.00002058407,0.00004802429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7481546,"threshold_uncertainty_score":0.9998476,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07078098645669183,"score_gpt":0.2016197265179104,"score_spread":0.1308387400612186,"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."}}