University of Birmingham > Talks@bham > Data Science and Computational Statistics Seminar > Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path space

## Solving high-dimensional Hamilton-Jacobi-Bellman PDEs using neural networks: perspectives from the theory of controlled diffusions and measures on path spaceAdd to your list(s) Download to your calendar using vCal - Nikolas NÃ¼sken (University of Potsdam)
- Tuesday 01 September 2020, 13:00-14:00
- https://zoom.us/j/3264147316?pwd=S1ZZMS81UzRjRnp3NlFTcWFPOVpnZz09.
If you have a question about this talk, please contact Hong Duong. The first part of this presentation will review connections between problems in the optimal control of diffusion processes, Hamilton-Jacobi-Bellman equations and forward-backward SDEs, having in mind applications in rare event simulation and stochastic filtering. The second part will explain a recent approach based on divergences between probability measures on path space and variational inference that can be used to construct appropriate loss functions in a machine learning framework. This is joint work with Lorenz Richter. This talk is part of the Data Science and Computational Statistics Seminar series. ## This talk is included in these lists:- Data Science and Computational Statistics Seminar
- https://zoom.us/j/3264147316?pwd=S1ZZMS81UzRjRnp3NlFTcWFPOVpnZz09
Note that ex-directory lists are not shown. |
## Other listsAnalysis Reading Seminar Type the title of a new list here Birmingham and Warwick Algebra Seminar## Other talksThe n-queens problem Towards a 1-dependent version of the Harris--Kesten theorem Stability of sharp Fourier restriction to spheres Duality Approach to the Spectral Statistics TBA Efficient Bayesian parameter inference for high-dimensional stochastic biological systems using an approximation |