Continuous Maassen kernels and the inverse oscillator
Dans ce travail, nous définissons et étudions la notion de “différentiabilité stochastique” d’une fonction définie sur un ouvert fin d’une variété riemannienne de dimension finie. Nous démontrons ensuite qu’une fonction admettant une “suite d’approximation forte” est, quasi-partout, stochastiquement indéfiniment différentiable et nous appliquons ces résultats à une classe de fonctions finement harmoniques.
We consider multi-dimensional gaussian processes and give a new condition on the covariance, simple and sharp, for the existence of Lévy area(s). gaussian rough paths are constructed with a variety of weak and strong approximation results. Together with a new RKHS embedding, we obtain a powerful – yet conceptually simple – framework in which to analyze differential equations driven by gaussian signals in the rough paths sense.
We give a complete analytical characterization of the functions transforming reflected Brownian motions to local Dirichlet processes.
Let D be either a convex domain in or a domain satisfying the conditions (A) and (B) considered by Lions and Sznitman (1984) and Saisho (1987). We investigate convergence in law as well as in for the Euler and Euler-Peano schemes for stochastic differential equations in D with normal reflection at the boundary. The coefficients are measurable, continuous almost everywhere with respect to the Lebesgue measure, and the diffusion coefficient may degenerate on some subsets of the domain.
We study convergence in law for the Euler and Euler-Peano schemes for stochastic differential equations reflecting on the boundary of a general convex domain. We assume that the coefficients are measurable and continuous almost everywhere with respect to the Lebesgue measure. The proofs are based on new estimates of Krylov's type for the approximations considered.