{"id":"W4415111878","doi":"10.48550/arxiv.2506.12553","title":"Beyond Laplace and Gaussian: Exploring the Generalized Gaussian Mechanism for Private Machine Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Auction Theory and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Toronto; Canadian Institute for Advanced Research; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Differential privacy; Laplace transform; Gaussian; Dimension (graph theory); Gaussian noise; Mechanism (biology); Noise (video); Extension (predicate logic)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.01758991,0.0009748655,0.001750971,0.001228847,0.001226989,0.004619777,0.004000173,0.002749121,0.003013065],"category_scores_gemma":[0.04084493,0.0008225972,0.001812431,0.002137227,0.006702828,0.01155822,0.006057906,0.006178415,0.000543435],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002816751,"about_ca_system_score_gemma":0.003787458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001237752,"about_ca_topic_score_gemma":0.001065569,"domain_scores_codex":[0.9880333,0.007500674,0.0002788977,0.001325095,0.00215456,0.0007073897],"domain_scores_gemma":[0.9691712,0.02093208,0.001459545,0.006793688,0.001038781,0.0006047224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001598262,0.0001081345,0.0009966299,0.00009220366,0.00005839008,0.00008770925,0.0001805276,0.06235053,0.0007180696,0.8990268,0.001755334,0.03446588],"study_design_scores_gemma":[0.000063023,0.00007663118,0.0001557824,0.00003029511,0.00001421399,0.00009480744,0.00003122663,0.2457388,0.0006608522,0.7502413,0.002870873,0.00002217222],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02141855,0.0007998439,0.9694163,0.002621819,0.00004390909,0.00008403786,0.0001005257,0.0002884566,0.005226581],"genre_scores_gemma":[0.770658,0.001370673,0.2212292,0.001495275,0.0002122848,0.0003268607,0.0001530724,0.0001736974,0.00438096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01758991,"threshold_uncertainty_score":0.09302545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1561771792642622,"score_gpt":0.3651035741737756,"score_spread":0.2089263949095134,"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."}}