{"id":"W3204160450","doi":"10.1007/978-3-030-88428-4_27","title":"Training Differentially Private Neural Networks with Lottery Tickets","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Lottery; Computer science; Ticket; Margin (machine learning); Artificial neural network; Quality (philosophy); Function (biology); Machine learning; Artificial intelligence; Deep neural networks; Computer security; Microeconomics","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":[0.003081938,0.0008950121,0.001302682,0.0004747746,0.0005811091,0.00156564,0.002179322,0.002197828,0.005667857],"category_scores_gemma":[0.01210989,0.001030979,0.0007216986,0.0006186303,0.001766604,0.005229995,0.003386663,0.003815095,0.0011326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001374374,"about_ca_system_score_gemma":0.001260854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001314237,"about_ca_topic_score_gemma":0.002518817,"domain_scores_codex":[0.998841,0.0004430611,0.00008002303,0.0002484886,0.0002191388,0.0001683453],"domain_scores_gemma":[0.995464,0.003230689,0.0002245491,0.0007597551,0.0002089917,0.0001120956],"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":[0.0007470462,0.0002504775,0.0008241091,0.0001166525,0.0001126659,0.00007761805,0.00009903406,0.7780913,0.00224925,0.08643801,0.003993493,0.1270003],"study_design_scores_gemma":[0.00002816783,0.00004462682,0.00005669837,0.00001316567,0.000008313375,0.00001199872,0.000007590832,0.9481348,0.0007544381,0.05063536,0.000298365,0.00000644665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08704842,0.001032878,0.9004034,0.001728432,0.0003276464,0.00009243005,0.0002028003,0.001323035,0.007840881],"genre_scores_gemma":[0.8883905,0.000437324,0.09516397,0.0004671868,0.0002497345,0.0001926972,0.0003802422,0.0001494504,0.01456889],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005667857,"threshold_uncertainty_score":0.01896089,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03400915162097332,"score_gpt":0.2471313070363142,"score_spread":0.2131221554153409,"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."}}