Get Started
Research questionHow can smooth density estimation preserve accuracy under relaxed local differential privacy?Local privacy can make each observation substantially less informative, degrading density estimates especially for smooth-function classes. The challenge is to protect individual observations while retaining accuracy closer to the nonprivate setting.
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Faster Learning under Relaxed Local Differential PrivacyThe source studies α-TV-LDP density estimation using independent symmetrized Gamma noise and deconvolution for r-Sobolev densities. It provides pointwise-rate results, a smoothness-adaptive procedure, and numerical results for a neural estimator that compares this mechanism with Laplace noise and private SGD.research paper · Sep 4, 2026
Related questions
How can differentially private high-dimensional LASSO stay stable with heterogeneous covariate scales without privacy-costly preprocessing?How can noisy Lipschitz regression recover an unknown function uniformly on a general metric space?How can mesh-free differential operators stay accurate at high resolvable wavenumbers on disordered nodes?What are the fundamental sample-size limits for estimating diffusion-based local intrinsic dimension at finite smoothing scales?
Home
Topics
Search
Library