Nonparametric Bayesian estimation in a multidimensional diffusion model with high frequency data

Abstract

We consider nonparametric Bayesian inference in a multidimensional diffusion model with reflecting boundary conditions based on discrete high-frequency observations. We prove a general posterior contraction rate theorem in $L^2$-loss, which is applied to Gaussian priors. The resulting posteriors, as well as their posterior means, are shown to converge to the ground truth at the minimax optimal rate over Hölder smoothness classes in any dimension. Of independent interest and as part of our proofs, we show that certain frequentist penalized least squares estimators are also minimax optimal.

61 pages, 1 figure, to appear in Probability Theory and Related Fields

References in corpus (18)

• Bayesian inverse problems with Gaussian priors
• Penalized nonparametric mean square estimation of the coefficients of diffusion processes
• Nonparametric estimation of scalar diffusions based on low frequency data
• Nonparametric Bayesian posterior contraction rates for discretely observed scalar diffusions
• Asymptotic statistical equivalence for ergodic diffusions: the multidimensional case
• Guided proposals for simulating multi-dimensional diffusion bridges
• Bayesian inference with rescaled Gaussian process priors
• Rates of contraction for posterior distributions in $\bolds{L^r}$-metrics, $\bolds{1\le r\le\infty}$
• Approximate Bayes learning of stochastic differential equations
• Nonparametric statistical inference for drift vector fields of multi-dimensional diffusions
• Bayesian estimation of discretely observed multi-dimensional diffusion processes using guided proposals
• Consistent nonparametric Bayesian inference for discretely observed scalar diffusions
• Gaussian process methods for one-dimensional diffusions: optimal rates and adaptation
• Nonparametric Bayesian inference for reversible multi-dimensional diffusions
• Non-parametric Bayesian drift estimation for stochastic differential equations
• A Bayesian nonparametric approach to log-concave density estimation
• A regularity class for the roots of non-negative functions
• Small-time expansion of the Fokker-Planck kernel for space and time dependent diffusion and drift coefficients