The Tractability Landscape of Sampling with Inexact Scores
Anming Gu, Kevin Tian, Hubert Yang, Yusong Zhu
stat.ML cs.LG math.ST
Abstract
We provide a simple and tight characterization of the types of inexact score oracle access that permit sampling with vanishing total variation bias, for a standard, well-behaved target family. Our main result shows that any weaker error than the sub-Gaussian assumption used by [YW26] rules out the tractability of unbiased sampling. This strengthens the conclusion of [CCSW26] to be algorithm-agnostic, and to hold for a wider range of error assumptions.
Topics
Classified with taxonomy v2 on Wed, 2 Sept 2026.