aiqbench analysis
This paper establishes fundamental limits on sampling algorithms when using inexact score oracles, proving that sub-Gaussian error assumptions are necessary to achieve vanishing total variation bias under standard conditions. By strengthening previous findings into an algorithm-agnostic result, it clarifies the theoretical boundaries for unbiased sampling across a wider range of error models without relying on specific implementation details.
The Tractability Landscape of Sampling with Inexact Scores
arXiv:2607.19004v1 Announce Type: cross 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.
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.
Machine Learning (stat.ML); Machine Learning (cs.LG); Statistics Theory (math.ST)
arXiv:2607.19004 [stat.ML]
(or arXiv:2607.19004v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2607.19004 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 170 words
