Interacting particle Langevin algorithm for maximum marginal likelihood estimation

¹ Department of Mathematics, Imperial College London, UK
² Department of Economics, Social Studies, Applied Mathematics and Statistics, University of Turin, Italy
³ Department of Engineering, University of Cambridge and The Alan Turing Institute, UK
⁴ Universite Paris Dauphine, Paris, France
⁵ School of Mathematics, University of Edinburgh, UK; The Alan Turing Institute, UK; National Technical University of Athens, Athens, Greece.

^* Corresponding author: T.Johnston-4@sms.ed.ac.uk

Received: 12 April 2024
Accepted: 3 March 2025

Abstract

We develop a class of interacting particle systems for implementing a maximum marginal likelihood estimation (MMLE) procedure to estimate the parameters of a latent variable model. We achieve this by formulating a continuous-time interacting particle system which can be seen as a Langevin diffusion over an extended state space of parameters and latent variables. In particular, we prove that the parameter marginal of the stationary measure of this diffusion has the form of a Gibbs measure where number of particles acts as the inverse temperature parameter in classical settings for global optimisation. Using a particular rescaling, we then prove geometric ergodicity of this system and bound the discretisation error in a manner that is uniform in time and does not increase with the number of particles. The discretisation results in an algorithm, termed Interacting Particle Langevin Algorithm (IPLA) which can be used for MMLE. We further prove nonasymptotic bounds for the optimisation error of our estimator in terms of key parameters of the problem, and also extend this result to the case of stochastic gradients covering practical scenarios.We provide numerical experiments to illustrate the empirical behaviour of our algorithm in the context of logistic regression with verifiable assumptions. Our setting provides a straightforward way to implement a diffusion-based optimisation routine compared to more classical approaches such as the Expectation Maximisation (EM) algorithm, and allows for especially explicit nonasymptotic bounds.