3 papers
cs.LG2026
When Diffusion Model Can Ignore Dimension: An Entropy-Based Theory
Ahmad Aghapour, Erhan Bayraktar
Diffusion models perform remarkably well on high-dimensional data such as images, often using only a modest number of reverse-time steps. Despite this practical success, existing c…
cs.LG2026
Conditional Diffusion Under Linear Constraints: Langevin Mixing and Information-Theoretic Guarantees
Ahmad Aghapour, Erhan Bayraktar, Asaf Cohen
We study zero-shot conditional sampling with pretrained diffusion models for linear inverse problems, including inpainting and super-resolution. In these problems, the observation…
math.PR2024
Strong equivalence between metrics of Wasserstein type
Erhan Bayraktar, Gaoyue Guo
We appended an errata to the original submission. The purpose of this errata is to point out two errors in [2] and give a weakened version of those statements made.