5 papers
Control Variate Score Matching for Diffusion Models
Khaled Kahouli, Romuald Elie, Klaus-Robert Müller +3
Diffusion models offer a robust framework for sampling from unnormalized probability densities, which requires accurately estimating the score of the noise-perturbed target distrib…
Optimised Annealed Sequential Monte Carlo Samplers
Saifuddin Syed, Alexandre Bouchard-Côté, Kevin Chern +1
Annealed Sequential Monte Carlo (ASMC) samplers are special cases of SMC samplers where the sequence of distributions can be embedded in a smooth path of distributions. Using this…
Source Separation by Flow Matching
Robin Scheibler, John R. Hershey, Arnaud Doucet +1
We consider the problem of single-channel audio source separation with the goal of reconstructing sources from their mixture. We address this ill-posed problem with FLOSS (FLOw…
An energy-based model approach to rare event probability estimation
Lea Friedli, David Ginsbourger, Arnaud Doucet +1
The estimation of rare event probabilities plays a pivotal role in diverse fields. Our aim is to determine the probability of a hazard or system failure occurring when a quantity o…
On the Asymptotics of Importance Weighted Variational Inference
Badr-Eddine Cherief-Abdellatif, Randal Douc, Arnaud Doucet +1
For complex latent variable models, the likelihood function is not available in closed form. In this context, a popular method to perform parameter estimation is Importance Weighte…