The Tractability Landscape of Sampling with Inexact Scores

Anming Gu; Kevin Tian; Hubert Yang; Yusong Zhu

The Tractability Landscape of Sampling with Inexact Scores

Machine Learning 2026-07-21 v1 Machine Learning Statistics Theory

Authors: Anming Gu , Kevin Tian , Hubert Yang , Yusong Zhu

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.

Keywords

sampling inexact score total variation tractability sub-Gaussian

Cite

@article{arxiv.2607.19004,
  title  = {The Tractability Landscape of Sampling with Inexact Scores},
  author = {Anming Gu and Kevin Tian and Hubert Yang and Yusong Zhu},
  journal= {arXiv preprint arXiv:2607.19004},
  year   = {2026}
}

Comments

5 pages, 1 figure