{"id":"W4404663741","doi":"10.1613/jair.1.15985","title":"Differentially Private Neural Tangent Kernels (DP-NTK) for Privacy-Preserving Data Generation","year":2024,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Novo Nordisk; Natural Sciences and Engineering Research Council of Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Computer science; Generator (circuit theory); Metric (unit); Benchmark (surveying); Synthetic data; Tangent; Artificial intelligence; Differential privacy; Data mining; Quality (philosophy); Machine learning; Pattern recognition (psychology); Mathematics; Power (physics)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003608606,0.0005347777,0.0008283778,0.0005321529,0.0004897549,0.001509037,0.001733229,0.001220389,0.001856221],"category_scores_gemma":[0.02034651,0.0002959137,0.0006563206,0.0009216383,0.001435639,0.003829606,0.003405273,0.002332266,0.0007072712],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001237194,"about_ca_system_score_gemma":0.001439915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006195156,"about_ca_topic_score_gemma":0.0006440317,"domain_scores_codex":[0.9968147,0.001162622,0.0002623532,0.0006022998,0.0009571322,0.0002009007],"domain_scores_gemma":[0.9912392,0.003158966,0.0006606316,0.004055073,0.0006661967,0.0002197936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001037242,0.0002611368,0.004623771,0.0003082309,0.0001146118,0.0003863557,0.0004223521,0.3612359,0.0178741,0.1815303,0.006269848,0.4259362],"study_design_scores_gemma":[0.0000347496,0.0001311703,0.0004714942,0.00002516037,0.00001538432,0.0003288042,0.00004360993,0.9039662,0.01255013,0.0792812,0.003121103,0.00003098828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02764164,0.0002877744,0.9694007,0.0003224965,0.00004030432,0.00007716244,0.0002978427,0.0007927769,0.001139316],"genre_scores_gemma":[0.8085852,0.0002584229,0.1867809,0.0002632533,0.00005547109,0.0001873264,0.000818779,0.0001988228,0.002851879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003608606,"threshold_uncertainty_score":0.01908433,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3973325884084702,"score_gpt":0.4591663783214747,"score_spread":0.06183378991300453,"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."}}