{"id":"W4388130980","doi":"10.3934/era.2023356","title":"Privacy amplification for wireless federated learning with Rényi differential privacy and subsampling","year":2023,"lang":"en","type":"article","venue":"Electronic Research Archive","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Federated learning; Differential privacy; Overhead (engineering); Computer science; MNIST database; Scheme (mathematics); Wireless; Transmission (telecommunications); Convergence (economics); Information privacy; Key (lock); Process (computing); Machine learning; Artificial intelligence; Computer network; Computer security; Telecommunications; Data mining; Deep learning; Mathematics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007587119,0.0007694822,0.001483207,0.0008775949,0.0009941491,0.002065168,0.002393443,0.0013523,0.0017049],"category_scores_gemma":[0.02333082,0.0004268582,0.001012778,0.001885008,0.002164418,0.004923249,0.004444974,0.002176616,0.0003462413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001834387,"about_ca_system_score_gemma":0.001870654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009222913,"about_ca_topic_score_gemma":0.0007227375,"domain_scores_codex":[0.9936118,0.002783641,0.0003449948,0.001118809,0.00151031,0.0006304415],"domain_scores_gemma":[0.9877023,0.006886125,0.0008887327,0.003180104,0.001031391,0.0003112836],"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":[0.001051439,0.0002379824,0.002704982,0.0002231812,0.0001949803,0.0003855169,0.000437461,0.5040376,0.01082552,0.2649845,0.003716217,0.2112007],"study_design_scores_gemma":[0.00002679005,0.00009185875,0.0001965459,0.00001168541,0.00001854213,0.0001379138,0.00003931702,0.9335589,0.003658945,0.06143549,0.0008062283,0.0000178417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02379866,0.0001831604,0.9742002,0.0003293547,0.00003696433,0.00005275591,0.00009118239,0.0002397939,0.001068002],"genre_scores_gemma":[0.8840952,0.0002456721,0.1126312,0.0003133982,0.00007721207,0.0001378635,0.000161823,0.00004899634,0.002288644],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007587119,"threshold_uncertainty_score":0.04012501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05946669298187045,"score_gpt":0.3439481834189567,"score_spread":0.2844814904370862,"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."}}