EconBase
← All papers

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

Huiming Zhang, Haoyu Wei, Guang Cheng

arXiv 13 Mar 2023 · Statistics — Machine Learning · 1 citations (OpenAlex)

arXiv:2303.07287 · PDF · DOI · OpenAlex · Extracted main text

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.

Citation extraction

43
references
75
in-text mentions
43
distinct cited
0
self-citations
12,204
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1B. Hao, Y. A. Yadkori, Z. Wen, and G. Cheng, Bootstrapping upper con… (2019) pp. 12123–121331.00094100%
2P. Auer, N. Cesa-Bianchi, and P. Fischer, Finite-time analysis of th… (2002) pp. 235–2560.92843100%
3V. V. Buldygin and I. V. Kozachenko, Metric characterization of rand… (2000)0.81142100%
4J. Lieber, Estimating concentration parameters for bandit algorithms (2022)0.81142100%
5P. J. Rousseeuw and S. Verboven, Robust estimation in very small sam… (2002) pp. 741–7580.73732100%
6M. J. Wainwright, High-dimensional statistics: A non-asymptotic view… (2019)0.73732100%
7H. Zhang and S. X. Chen, Concentration inequalities for statistical… (2021) pp. 1–850.73732100%
8S. Boucheron, G. Lugosi, and P. Massart, Concentration inequalities:… (2013)0.64422100%
9S. Arlot, G. Blanchard, E. Roquain, et al., Some nonasymptotic resul… (2010) pp. 51–820.51121100%
10N. Bettache, C. Butucea, and M. Sorba, Fast nonasymptotic testing an… (2021) p. 1048830.51121100%

Showing the top 10 of 43 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
12412.022511.00073
2Zero-Inflated Bandits0.00011