46
21

Nonparametric Bayesian posterior contraction rates for scalar diffusions with high-frequency data

Abstract

We consider inference in the scalar diffusion model dXt=b(Xt)dt+σ(Xt)dWtdX_t=b(X_t)dt+\sigma(X_t)dW_t with discrete data (XjΔn)0jn(X_{j\Delta_n})_{0\leq j \leq n}, n, Δn0n\to \infty,~\Delta_n\to 0 and periodic coefficients. For σ\sigma given, we prove a general theorem detailing conditions under which Bayesian posteriors will contract in L2L^2-distance around the true drift function b0b_0 at the frequentist minimax rate (up to logarithmic factors) over Besov smoothness classes. We exhibit natural nonparametric priors which satisfy our conditions. Our results show that the Bayesian method adapts both to an unknown sampling regime and to unknown smoothness.

View on arXiv
Comments on this paper