Differentiable Bayesian inference of SDE parameters using a pathwise series expansion of Brownian motion.
Sanmitra GhoshPaul J. BirrellDaniela De AngelisPublished in: AISTATS (2022)
Keyphrases
- bayesian inference
- brownian motion
- hyperparameters
- series expansion
- probabilistic model
- prior distribution
- prior information
- stochastic process
- optimal control
- maximum likelihood
- parameter estimation
- differential equations
- spherical harmonics
- poisson process
- diffusion process
- closed form solutions
- stochastic processes
- reinforcement learning
- heavy traffic
- closed form
- vector valued
- basis functions
- multiscale
- image processing