The Tractability Landscape of Sampling with Inexact Scores
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 5 of its 9 references that are in the map. First posted on arXiv 21 Jul 2026.
Builds on
5 of 9 references.
References · 5
- 2022Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptionscited by 445
- 2019Rapid Convergence of the Unadjusted Langevin Algorithm: Isoperimetry Sufficescited by 227
- 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptionscited by 219
- 2022Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Modelscited by 5
- 2026On the Robustness of Langevin Dynamics to Score Function Errorcited by 3
Built on by
Not cited yet.