works on

From the 2 of 13 linked papers with an AI index.

collaborators
Showing stat.MLShow all

7 papers · 1 filter

stat.ML2026

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…

stat.ML2026

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…

stat.ML2026

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…

stat.ML2026

Training Latent Diffusion Models with Interacting Particle Algorithms

Tim Y. J. Wang, Juan Kuntz, O. Deniz Akyildiz

We introduce a novel particle-based algorithm for end-to-end training of latent diffusion models. We reformulate the training task as minimizing a free energy functional and obtain…

stat.ML2026

Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation

Adam Rozzio, Rafael Athanasiades, O. Deniz Akyildiz

Maximum marginal likelihood estimation (MMLE) can be formulated as the optimization of a free energy functional. From this viewpoint, the Expectation-Maximisation (EM) algorithm ad…

stat.ML2025

A Gradient Flow Approach to Solving Inverse Problems with Latent Diffusion Models

Tim Y. J. Wang, O. Deniz Akyildiz

Solving ill-posed inverse problems requires powerful and flexible priors. We propose leveraging pretrained latent diffusion models for this task through a new training-free approac…