Post date: 04-Feb-2014 12:49:23
* 15h, Arnaud Guyader, Université Rennes 2
Simulation and Estimation of Extreme Quantiles and Extreme Probabilities
(joint work with Nicolas Hengartner and Eric Matzner-Løber)
Let X be a random vector with distribution μ on R^d and Phi be a mapping from R^d to R. That mapping acts as a black box, e.g., the result from some computer experiments for which no analytical expression is available. This paper presents an efficient algorithm to estimate a tail probability given a quantile or a quantile given a tail probability. The algorithm improves upon existing multilevel splitting methods and can be analyzed using Poisson process tools that lead to exact description of the distribution of the estimated probabilities and quantiles. The performance of the algorithm is demonstrated in a problem related to digital watermarking.
* 16h15, Nadia Oudjane, EDF R&D
A variance reduction technique for American options and application to power plant valuation
(joint work with P. Del Moral and P. HU)
Mathematically, the problem of pricing a power plant can be stated in terms of a stochastic optimal control problem and can be reduced in a very specific case to the thoroughly studied optimal stopping problem or American option pricing. In this talk, we present an original variance reduction approach for Bermudan option pricing (proposed in [1]) and extend this approach to apply it for valuating a thermal power plant w.r.t. the market.
Del Moral, P. HU and N. Oudjane, "Snell envelope with small probability criteria", Applied Mathematics & Optimization, Vol. 66, Issue 3, pp. 309-330, 2012