Full Name
Nima Anari
Job Title
Assistant Professor
University/Company
Stanford University
Speaking At
Abstract
I will talk about speeding up sampling via parallelism. We show surprising polynomial speedups (compared to sequential algorithms) are possible for sampling from *arbitrary* distributions in two settings: distributions on [q]^n accessed by conditional marginals (a la any-order autoregressive models), and distributions on R^n accessed by a denoising diffusion oracle.
