{"id":"W4391055620","doi":"10.1016/j.automatica.2024.111514","title":"Distributed empirical risk minimization with differential privacy","year":2024,"lang":"en","type":"article","venue":"Automatica","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Knut och Alice Wallenbergs Stiftelse; Natural Sciences and Engineering Research Council of Canada; Japan Society for the Promotion of Science London; International Federation of Automatic Control; Vetenskapsrådet; Stiftelsen för Strategisk Forskning","keywords":"Differential privacy; Benchmark (surveying); Computer science; Mathematical optimization; Convergence (economics); Noise (video); Minification; Empirical risk minimization; Dual (grammatical number); Convex optimization; Optimization problem; Constraint (computer-aided design); Class (philosophy); Fraction (chemistry); Regular polygon; Algorithm; Mathematics; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0001250142,0.0001689303,0.0001671678,0.0001277483,0.0001121133,0.0005096411,0.009972299,0.0001038488,0.00005468795],"category_scores_gemma":[0.005215652,0.000122848,0.00004295919,0.0008442255,0.0001015184,0.0006002042,0.01941914,0.0002561663,0.0001665848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000701259,"about_ca_system_score_gemma":0.00008601935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006617267,"about_ca_topic_score_gemma":0.000001989973,"domain_scores_codex":[0.9985062,0.0000778497,0.0002401623,0.0005086213,0.0003602433,0.0003068477],"domain_scores_gemma":[0.9949859,0.0003014765,0.00006405128,0.004545498,0.0000368922,0.00006620643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000144003,0.0002583144,0.006999386,0.0002313168,0.0002658292,0.0001761829,0.0006337683,0.00005218046,0.0001843219,0.01604463,0.8737127,0.101427],"study_design_scores_gemma":[0.0001481745,0.00007535607,0.01316617,0.000087293,0.00002681578,0.00002659097,0.000006090085,0.9127984,0.0005801877,0.06933935,0.003563828,0.000181716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05897827,0.00005655,0.9150526,0.02065162,0.0002555244,0.0001640291,0.00005665518,0.004531878,0.0002528748],"genre_scores_gemma":[0.6912603,0.00001584261,0.3085479,0.00003191584,0.00003131862,0.00002465828,0.00005529159,0.00001370356,0.00001908238],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9127463,"threshold_uncertainty_score":0.9953842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02200699237123229,"score_gpt":0.2847832294224054,"score_spread":0.2627762370511731,"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."}}