English

Tight Non-asymptotic Inference via Sub-Gaussian Intrinsic Moment Norm

Machine Learning 2026-03-16 v3 Machine Learning Econometrics

Abstract

In non-asymptotic learning, variance-type parameters of sub-Gaussian distributions are of paramount importance. However, directly estimating these parameters using the empirical moment generating function (MGF) is infeasible. To address this, we suggest using the sub-Gaussian intrinsic moment norm [Buldygin and Kozachenko (2000), Theorem 1.3] achieved by maximizing a sequence of normalized moments. Significantly, the suggested norm can not only reconstruct the exponential moment bounds of MGFs but also provide tighter sub-Gaussian concentration inequalities. In practice, we provide an intuitive method for assessing whether data with a finite sample size is sub-Gaussian, utilizing the sub-Gaussian plot. The intrinsic moment norm can be robustly estimated via a simple plug-in approach. Our theoretical findings are also applicable to reinforcement learning, including the multi-armed bandit scenario.

Keywords

Cite

@article{arxiv.2303.07287,
  title  = {Tight Non-asymptotic Inference via Sub-Gaussian Intrinsic Moment Norm},
  author = {Huiming Zhang and Haoyu Wei and Guang Cheng},
  journal= {arXiv preprint arXiv:2303.07287},
  year   = {2026}
}

Comments

This manuscript has been withdrawn by the authors as it is not yet ready for public release. Further improvements and revisions are required before a final version can be considered for distribution