Abstract
The object of this paper is a one-dimensional generalized porous media equation (PDE) with possibly discontinuous coefficient β , which is well-posed as an evolution problem in L 1(R) In some recent papers of Blanchard et al. and Barbu et al., the solution was represented by the solution of a non-linear stochastic differential equation in law if the initial condition is a bounded integrable function. We first extend this result, at least when β is continuous and the initial condition is only integrable with some supplementary technical assumption. The main purpose of the article is to introduce and implement a stochastic particle algorithm to approach the solution to PDE, which also fits in the case when β is irregular. We compare it with some recent numerical deterministic techniques. As a byproduct, we can predict the long-time behavior of the solution in several cases.
| Original language | English |
|---|---|
| Pages (from-to) | 317-369 |
| Number of pages | 53 |
| Journal | Monte Carlo Methods and Applications |
| Volume | 17 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 1 Dec 2011 |
Keywords
- Stochastic particle algorithm
- kernel estimator
- monotonicity
- non-parametric density estimation
- porous media equation
- stochastic differential equations