Deep Learning for the Benes Filter

  title={Deep Learning for the Benes Filter},
  author={Alexander Lobbe},
The Benes filter is a well-known continuous-time stochastic filtering model in one dimension that has the advantage of being explicitly solvable. From an evolution equation point of view, the Benes filter is also the solution of the filtering equations given a particular set of coefficient functions. In general, the filtering stochastic partial differential equations (SPDE) arise as the evolution equations for the conditional distribution of an underlying signal given partial, and possibly… 

Figures from this paper

An energy-based deep splitting method for the nonlinear filtering problem

A deep splitting method is combined with an energy-based model for the approximation of functions by a deep neural network to result in a computationally fast nonlinear learner that takes observations as input and that does not require re-training when new observations are received.

Designing Universal Causal Deep Learning Models: The Case of Infinite-Dimensional Dynamical Systems from Stochastic Analysis

This paper proposes a “geometry-aware” DL model-design framework that takes a suitable infinite-dimensional linear metric spaces as inputs and returns a universal sequential DL models adapted to these linear geometries, and calls these models Causal Neural Operators (CNO), deducing that the CNO can approximate the solution operator to most stochastic problems.



An application of the splitting-up method for the computation of a neural network representation for the solution for the filtering equations

A PDE inspired method with a neural network representation inspired by Han et al. is used to produce an approximation of the unnormalised conditional distribution of the signal process and is tested with numerical approximation results for the Kalman and Benes filter.

Solving stochastic differential equations and Kolmogorov equations by means of deep learning

A numerical approximation method is derived and proposed which aims to overcome both of the above mentioned drawbacks and intends to deliver a numerical approximation of the Kolmogorov PDE on an entire region without suffering from the curse of dimensionality.

Adam: A Method for Stochastic Optimization

This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.

Time discretization of nonlinear filtering equations

  • F. Le Gland
  • Mathematics
    Proceedings of the 28th IEEE Conference on Decision and Control,
  • 1989
Some computable approximate expressions are provided for the conditional law of diffusion processes observed in continuous time. The numerical schemes are derived through an approximation of the

Deep Learning

Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.

Fundamentals of Stochastic Filtering

Filtering Theory.- The Stochastic Process ?.- The Filtering Equations.- Uniqueness of the Solution to the Zakai and the Kushner-Stratonovich Equations.- The Robust Representation Formula.-

Numerical Solution of Stochastic Differential Equations

This paper provides an introduction to the main concepts and techniques necessary for someone who wishes to carryout numerical experiments involving Stochastic Differential Equation (SDEs). As SDEs

An Adaptive Local Grid Refinement Method for Nonlinear Filtering

La resolution numerique de l'equation de Zakai conduit generalement a des systemes d'equations qui doivent etre inverses a chaque pas de temps. Un algorithme pour l'approximation numerique de

Splitting-up approximation for SPDE's and SDE's with application to nonlinear filtering

A splitting-up approximation is introduced for diffusion processes, based on the successive composition of two stochastic flows of diffeomorphisms over a given partition of the time interval.

Brownian Motion and Stochastic Calculus

1 Preliminaries of Measure Theory De…nition 1 F P ( ) is said to be an algebra if (1) 2 F (2) A;B 2 F implies A S B 2 F (3) A 2 F implies AC 2 F . F is said to be a semialgebra or semi-ring is (1) ;?