The paper proves polynomial mixing time upper bounds for three data augmentation algorithms (ProbitDA, LogitDA, LassoDA) with explicit dependence on design matrix, prior, n, and d.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
Proves space-time LSI and hypocoercive hypercontractivity for underdamped Langevin dynamics, giving Rényi divergence decay at rate O(sqrt(rho)) under tuned friction.
Parallel Picard-map algorithms for zeroth-order Random Walk Metropolis achieve O(sqrt(d)) parallel iterations with O(sqrt(d)) processors on log-concave distributions in d dimensions.
Novel splitting scheme for kinetic Langevin sampling with exact harmonic integrator yields L2-Wasserstein convergence rates matching continuous dynamics and non-asymptotic error bounds for strongly log-concave targets.
citing papers explorer
-
Fast Mixing of Data Augmentation Algorithms: Bayesian Probit, Logit, and Lasso Regression
The paper proves polynomial mixing time upper bounds for three data augmentation algorithms (ProbitDA, LogitDA, LassoDA) with explicit dependence on design matrix, prior, n, and d.