Skip to Main content Skip to Navigation
Theses

Study and simulation of skew diffusion processes

Abstract : We consider the skew diffusion processes and their simulation. This study are divided into four parts and concentrate on the processes whose coefficients are piecewise constant with discontinuities along a simple hyperplane. We start by a theoretical study of the one-dimensional case when the coefficients belong to a broader class. We particularly give a result on the structure of the resolvent densities of these processes and obtain a computational method. When it is possible, we perform a Laplace inversion of these densities and provide some transition functions. Then we concentrate on the simulation of skew diffusions process. We build a numerical scheme using the resolvent density for any Feller processes. With this scheme and the resolvent densities computed in the previous part, we obtain a simulation method for the skew diffusion processes in dimension one. After that, we consider the multidimensional case. We provide a theoretical study and compute some functionals of the skew diffusions processes. This allows to obtain among others the transition function of the marginal process orthogonal to the hyperplane of discontinuity. Finally, we consider the parallelization of Monte Carlo methods. We provide a strategy which allows to simulate a large batch of skew diffusions processes sample paths on massively parallel architecture. An interesting feature is the possibility to replay some the sample paths of previous simulations.
Complete list of metadata

Cited literature [82 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01247310
Contributor : Abes Star :  Contact
Submitted on : Wednesday, March 9, 2016 - 3:35:19 PM
Last modification on : Thursday, January 7, 2021 - 4:13:38 PM

File

LENOTRE_Lionel.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01247310, version 2

Citation

Lionel Lenôtre. Study and simulation of skew diffusion processes. Probability [math.PR]. Université Rennes 1, 2015. English. ⟨NNT : 2015REN1S079⟩. ⟨tel-01247310v2⟩

Share

Metrics

Record views

441

Files downloads

554