Showing math.STShow all
2 papers · 1 filter
math.ST2026
Wasserstein Bounds for Euler and Randomized Midpoint Langevin Sampling with Noisy Gradients
Yifei Xiong, Vinayak Rao
Stochastic-gradient Langevin methods are sampling algorithms that replace the gradient of the log probability density by a noisy, possibly biased evaluation. We study how such grad…
math.ST2026
Statistical Properties of Nonparametric MLE under Laplace Noise
Yifei Xiong, Nianqiao Phyllis Ju, Vinayak Rao
Local differential privacy (LDP) protects individuals in a dataset by perturbing each measurement before release. For real-valued data, a widely used mechanism is additive Laplace…