Abstract
The pricing of Bermudan options amounts to solving a dynamic programming
principle, in which the main difficulty, especially in high dimension, comes
from the conditional expectation involved in the computation of the
continuation value. These conditional expectations are classically computed by
regression techniques on a finite-dimensional vector space. In this work, we
study neural networks approximations of conditional expectations.
We prove the convergence of the well-known Longstaff and Schwartz algorithm when the
standard least-square regression is replaced by a neural network
approximation, assuming an efficient algorithm to compute this approximation.
We illustrate the numerical efficiency of neural networks as an
alternative to standard regression methods for approximating conditional
expectations on several numerical examples.