4 papers
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…
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…
Entropy-Based Dimension-Free Convergence and Loss-Adaptive Schedules for Diffusion Models
Ahmad Aghapour, Erhan Bayraktar, Ziqing Zhang
Diffusion generative models synthesize samples by discretizing reverse-time dynamics driven by a learned score (or denoiser). Existing convergence analyses of diffusion models typi…
Dynamic data generation and dynamic portfolio selection: an application of a score-based diffusion model
Ahmad Aghapour, Erhan Bayraktar, Fengyi Yuan
We study dynamic data generation and its application to model-free dynamic portfolio selection. Existing score-based diffusion models are typically designed to learn a static data…