From the 2 of 13 linked papers with an AI index.
13 papers
Particle-based Generalised Stochastic Optimisation
Jiechen Jackie Zhang, O. Deniz Akyildiz
We develop a class of diffusion-based stochastic particle optimisation methods for loss functions with intractable gradients. Specifically, we consider problems in which the loss g…
Learning Latent Energy-Based Models via Interacting Particle Langevin Dynamics
Joanna Marks, Tim Y. J. Wang, O. Deniz Akyildiz
The paper proposes a continuous‑time framework using interacting particle Langevin dynamics to learn latent variable models with energy‑based priors, provides a discretized algorit…
An Operator-Theoretic Analysis of Nonlinear Filtering under Model Misspecification
Fabián González, Ãmer Deniz Akyildiz, Dan Crisan +1
The paper analyzes how Bayesian nonlinear filters behave when the assumed model dynamics are misspecified, providing explicit error bounds that separate the impact of initial error…
A Multiscale Perspective on Maximum Marginal Likelihood Estimation
O. Deniz Akyildiz, Michela Ottobre, Iain Souttar
In this paper, we provide a multiscale perspective on the problem of maximum marginal likelihood estimation. We consider and analyse a diffusion-based maximum marginal likelihood e…
Efficient Stochastic Optimisation via Sequential Monte Carlo
James Cuin, Davide Carbone, Yanbo Tang +1
The problem of optimising functions with intractable gradients frequently arises in machine learning and statistics, ranging from maximum marginal likelihood estimation procedures…
Kinetic Interacting Particle Langevin Monte Carlo
Paul Felix Valsecchi Oliva, O. Deniz Akyildiz
This paper introduces and analyses interacting underdamped Langevin algorithms, termed Kinetic Interacting Particle Langevin Monte Carlo (KIPLMC) methods, for statistical inference…