Non-asymptotic estimates for accelerated high order Langevin Monte Carlo algorithms

arXiv:2405.05679v1 Announce Type: cross
Abstract: In this paper, we propose two new algorithms, namely aHOLA and aHOLLA, to sample from high-dimensional target distributions with possibly super-linearly growing potentials. We establish non-asymptotic convergence bounds for aHOLA in Wasserstein-1 and Wasserstein-2 distances with rates of convergence equal to $1+q/2$ and $1/2+q/4$, respectively, under a local H\"{o}lder condition with exponent $q\in(0,1]$ and a convexity at infinity condition on the potential of the target distribution. Similar results are obtained for aHOLLA under certain global …

abstract algorithms arxiv convergence equal math.pr math.st paper sample stat.co stat.ml stat.th type