From the 1 of 25 linked papers with an AI index.
1 citations · 1 across the 11 of their papers we have counts for
5 papers · 1 filter
Spectral Diffusion Processes
Angus Phillips, Thomas Seror, Michael Hutchinson +3
The paper introduces diffusion models for stochastic processes by representing data in a spectral domain using kernels, truncating the spectral coefficients, and modeling them with…
Self-Speculative Masked Diffusions
Andrew Campbell, Valentin De Bortoli, Jiaxin Shi +1
We present self-speculative masked diffusions, a new class of masked diffusion generative models for discrete data that require significantly fewer function evaluations to generate…
Dimension-free error estimate for diffusion model and optimal scheduling
Valentin de Bortoli, Romuald Elie, Anna Kazeykina +2
Diffusion generative models have emerged as powerful tools for producing synthetic data from an empirically observed distribution. A common approach involves simulating the time-re…
From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
Marien Renaud, Valentin De Bortoli, Arthur Leclaire +1
We consider the problem of sampling distributions stemming from non-convex potentials with Unadjusted Langevin Algorithm (ULA). We prove the stability of the discrete-time ULA to d…
Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
Marien Renaud, Jiaming Liu, Valentin de Bortoli +2
Posterior sampling has been shown to be a powerful Bayesian approach for solving imaging inverse problems. The recent plug-and-play unadjusted Langevin algorithm (PnP-ULA) has emer…