5 papers
The information geometry of product-reference discrete diffusion: Interaction growth complexity and optimal scheduling
Martin J. Wainwright
We study a class of product-reference diffusion algorithms for sampling from a discrete distribution. We show that their sampling performance can be characterized using a path-base…
The data geometry of masking diffusion: Certified-optimal schedules via unmasking growth complexity
Martin J. Wainwright
We study masking diffusion for discrete sampling and introduce a path-resolved measure of data geometry called the \emph{unmasking growth complexity} ({\textsf{UGC}\xspace}). Its l…
Denoising growth complexity: Data geometry and certified schedules for diffusion sampling
Martin J. Wainwright
Two central challenges in diffusion-based sampling are the theoretical one of understanding their remarkable effectiveness even in high-dimensional settings, and the practical one…
TILT: Target-induced loss tilting under covariate shift
Kakei Yamamoto, Martin J. Wainwright
We introduce and analyze Target-Induced Loss Tilting (TILT) for unsupervised domain adaptation under covariate shift. It is based on a novel objective function that decomposes the…
Fast Score-Based Sampling via Log-Concave Reductions
M. J. Wainwright
Sampling based on score diffusions has led to striking empirical results, and has attracted considerable attention from various research communities. It depends on availability of…