Scientific Organisers:
-
Víctor Elvira, University of Edinburgh
-
Dan Crisan, Imperial College London
-
Jana de Wiljes, University of Potsdam
-
Joaquín Míguez, University Carlos III of Madrid
About:
Sequential Monte Carlo (SMC) methods, also known as particle filters or particle methods, have become popular and powerful tools for computational inference in complex probabilistic models used in many and varied fields and applications. The research community includes practitioners and theoreticians at the intersection of statistics, computer science, electrical engineering, and applied mathematics. The interest in SMC methods have rapidly grown in the last decade, jointly with the new challenges and the enormous potential of SMC to tackle high-impact problems in applied sciences (e.g., meteorology, biomedicine, robotics, etc.). The main objectives of the meeting were:
1. to bring together researchers developing and using SMC methods in a diversity of scientific and engineering fields, both in academia and the industry, and
2. to open the field to researchers and users who are new to SMC methods. We emphasized the interaction of SMC with related areas of research (such as machine learning or data science) where computational inference plays a key role.
Below, we provide a list of key theoretical and methodological topics, as well as application areas.
|
Theory & Methodology
|
Applications
|
Finally, this event was linked to the Summer School on Bayesian filtering: fundamental theory and numerical methods (SSBF), also held at ICMS on 6-10 May 2024.
Programme
| MONDAY 13 MAY 2024 | ||
| Registration and Refreshments | ||
| Welcome and Housekeeping | ||
| Christian Robert, Université Paris Dauphine PSL & University of Warwick | Sampling advances by adaptive regenerative processes and importance Monte Carlo | |
| Sahani Pathiraja, UNSW Sydney | Connections between sequential filtering and evolutionary dynamics | |
| Refreshments | ||
| Joaquín Míguez, Universidad Carlos III de Madrid | A Sequential Discretisation Scheme for Stochastic Differential Equations and Its Application to Bayesian Filtering | |
| Axel Finke, Loughborough University | Particle-MALA and Particle-mGRAD: Gradient-based MCMC methods for high-dimensional state-space models | |
| Lunch | ||
| Francesca Crucinio, King's College London | A connection between Tempering and Entropic Mirror Descent | |
| Fredrik Lindsten, Linköping University | Sequential Monte Carlo guidance of (discrete) diffusion models | |
| Refreshments | ||
| Poster session 1 | ||
| TUESDAY 14 MAY 2024 | ||
| Refreshments | ||
| Christophe Andrieu, University of Bristol | Monte Carlo sampling with integrator snippets | |
| Anthony Lee, University of Bristol | Mixing time of the conditional backward sampling particle filter | |
| Refreshments | ||
| Arnaud Doucet, University of Oxford & Google DeepMind | Diffusion models for Monte Carlo sampling | |
| Meetings & discussion | ||
| Lunch | ||
| Yunpeng Li, University of Surrey | Normalising flow-based differentiable particle filters | |
| Neil Chada, Heriot Watt University | Multilevel Bayesian Deep Neural Networks | |
| Refreshments | ||
| Poster session 2 | ||
| Conference Dinner | ||
| WEDNESDAY 15 MAY 2024 | ||
| Refreshments | ||
| Nick Whiteley, University of Bristol | Consistent and fast inference in compartmental models of epidemics using Poisson Approximate Likelihoods | |
| Jana de Wiljes, TU Ilmenau | ||
| Refreshments | ||
| Oana Lang, Imperial College London | Generative Modelling for a Stochastic Rotating Shallow Water System | |
| Meetings & discussion | ||
| Lunch | ||
| Nicola Branchini, University of Edinburgh | Generalizing self-normalized importance sampling with couplings | |
| Simo Särkkä, Aalto University | Parallel filtering and smoothing methods for state-space models | |
| Refreshments | ||
| Poster session 3 | ||
| THURSDAY 16 MAY 2024 | ||
| Refreshments | ||
| Pierre Del Moral, Inria | Some theoretical aspects of Particle Filters and Ensemble Kalman Filters | |
| Alexandros Beskos, University College London | Antithetic Multilevel Methods for Elliptic and Hypo-Elliptic Diffusions | |
| Refreshments | ||
| Daniel Paulin, University of Edinburgh | Unbiased Kinetic Langevin Monte Carlo with Inexact Gradients | |
| Adam Johansen, University of Warwick | Divide and Conquer Sequential Monte Carlo: Some Properties and Application | |
| Lunch | ||
| Meetings & discussion | ||
| FRIDAY 17 MAY 2024 | ||
| Refreshments | ||
| Sara Pérez Vieites, Aalto University | Learning the number of particles in nested filtering | |
| Marcelo Gomes da Silva Bruno, ITA, Brazil | Sequential Monte Carlo Methods for Distributed Bayesian Filtering on Manifolds | |
| Refreshments | ||
| Jeremy Heng, ESSEC Business School | Computational Doob's h-transforms for online filtering | |
| Nicolas Chopin, ENSAE Paris, IPP | Unbiased estimation of smooth functions | |
| Lunch and end of workshop |
