Thursday, April 26, 2018 - 17:15 in V2-210/216
CANCELLED: Deep Optimal Stopping
A talk in the Mathematisches Kolloquium (SFB 1283) series by
Patrick Cheridito from ETH Zürich
| Abstract: |
We develop a deep learning method for optimal stopping problems whichdirectly learns the optimal stopping rule from Monte Carlo samples. As such it is broadly applicablein situations where the underlying randomness can efficiently be simulated. We test themethod on two benchmark problems: the pricing of a Bermudan max-call optionon different underlying assets and the problem of optimally stopping a fractional Brownian motion.In both cases it produces very accurate results in high-dimensional situations with shortcomputing times.
|
Back
