Twisted: Improving particle filters by learning modified paths
Date: 22 April 2022, Friday
Time: 4pm AEDT
Speaker: Dr Joshua Bon (QUT)
Abstract:
Particle filters, and sequential Monte Carlo (SMC) more generally, operate by propagating weighted samples (or particles) through a sequence of distributions. Such a sequence is characterised by a Feynman-Kac model (or path measure) and chosen for the given inferential task at hand. One can also define twisted Feynman-Kac models which preserve the inferential target but provide a more efficient sequence of distributions (or path) for the SMC algorithm to use. Optimally twisted models define perfect Monte Carlo samplers and are therefore an important concept for SMC algorithms.
We investigate how to learn and use twisted Feynman-Kac models in situations where the original model involves difficult or intractable transition dynamics. This extends existing work which relies on twisting the model analytically. We achieve twisting via Monte Carlo and analyse the resulting algorithm through a random-weight SMC viewpoint. We run simulations to test the methods performance and provide an example on a stochastic volatility model.
This is joint work with Anthony Lee and Christopher Drovandi.
Time: 4pm AEDT
Speaker: Dr Joshua Bon (QUT)
Abstract:
Particle filters, and sequential Monte Carlo (SMC) more generally, operate by propagating weighted samples (or particles) through a sequence of distributions. Such a sequence is characterised by a Feynman-Kac model (or path measure) and chosen for the given inferential task at hand. One can also define twisted Feynman-Kac models which preserve the inferential target but provide a more efficient sequence of distributions (or path) for the SMC algorithm to use. Optimally twisted models define perfect Monte Carlo samplers and are therefore an important concept for SMC algorithms.
We investigate how to learn and use twisted Feynman-Kac models in situations where the original model involves difficult or intractable transition dynamics. This extends existing work which relies on twisting the model analytically. We achieve twisting via Monte Carlo and analyse the resulting algorithm through a random-weight SMC viewpoint. We run simulations to test the methods performance and provide an example on a stochastic volatility model.
This is joint work with Anthony Lee and Christopher Drovandi.
Link: https://unsw.zoom.us/j/87842437786?pwd=TVFWZUo3b2pOZXJ1MDBsZmxhQkV3QT09
Password: 641323
Password: 641323