The ANR project IPSO (Interacting Particle systems for Sampling and Optimization) was awarded to Urbain Vaes. The project will last two years starting 1st October 2023.
Many scientific applications require the calculation of expectations with respect to high-dimensional probability distributions. A widely-used approach to this end, known as the Markov chain Monte Carlo (MCMC) method, is to simulate a long trajectory of a stochastic dynamics that admits the target distribution as unique invariant measure, and to approximate expectations by time averages over this trajectory. Although the original MCMC method dates back to the 1950s, the development and analysis of sampling methods remains at present an extremely active area of mathematical research, driven by the ever-increasing amount of data available to scientists, a desire to understand high-dimensional problems, and changes in computer architecture.
Many key recent developments in the field are based on the use of interacting particle systems and their analysis at the level of the nonlocal Fokker-Planck equation describing the systems in the limit of infinitely many particles, known as the mean field limit. This approach to numerical algorithms based on interacting particle systems emerged initially from the optimization community and has since then brought considerable insight. It has enabled, notably, significant progress towards proving rigorously the longtime convergence of widely-used interacting particle methods, including the ensemble Kalman filter and particle swarm optimization.
Improving, implementing and mathematically analysing sampling and optimisation methods based on interacting particle systems are the primary aims of this project. The work we propose to undertake pertains to two particular classes of methods: consensus-based methods inspired by particle swarm optimisation, and ensemble Kalman-based methods, which were recently revealed to have a close connection to interacting Langevin diffusions. These methods have proven to be successful in variety of applications, including posterior sampling and maximum a posteriori estimation in the context of Bayesian inverse problems, as well as the training of large neural networks.
The planned research outlined in this project aims at laying the theoretical foundations of the emerging field of sampling and optimization using interacting particles and, when combined with modern computer architectures for parallel computing, has the potential to significantly impact applications.