2000 character limit reached
Correlated Binomial Process (2402.07058v1)
Published 10 Feb 2024 in math.PR
Abstract: Cohen and Kontorovich (COLT 2023) initiated the study of what we call here the Binomial Empirical Process: the maximal absolute value of a sequence of inhomogeneous normalized and centered binomials. They almost fully analyzed the case where the binomials are independent, and the remaining gap was closed by Blanchard and Vor\'{a}\v{c}ek (ALT 2024). In this work, we study the much more general and challenging case with correlations. In contradistinction to Gaussian processes, whose behavior is characterized by the covariance structure, we discover that, at least somewhat surprisingly, for binomial processes covariance does not even characterize convergence. Although a full characterization remains out of reach, we take the first steps with nontrivial upper and lower bounds in terms of covering numbers.
- M. Blanchard and V. Voráček. Tight bounds for local glivenko-cantelli. In Algorithmic Learning Theory, ALT 2024, Proceedings of Machine Learning Research. PMLR, 2024.
- O. Catoni. Challenging the empirical mean and empirical variance: a deviation study. In Annales de l’IHP Probabilités et statistiques, volume 48, pages 1148–1185, 2012.
- Fast mean estimation with sub-gaussian rates. In A. Beygelzimer and D. Hsu, editors, Conference on Learning Theory, COLT 2019, 25-28 June 2019, Phoenix, AZ, USA, volume 99 of Proceedings of Machine Learning Research, pages 786–806. PMLR, 2019. URL http://proceedings.mlr.press/v99/cherapanamjeri19b.html.
- Optimal mean estimation without a variance. CoRR, abs/2011.12433, 2020. URL https://arxiv.org/abs/2011.12433.
- The price of independence in a model with unknown dependence. Mathematical Social Sciences, 123:51–58, 2023. ISSN 0165-4896. doi: https://doi.org/10.1016/j.mathsocsci.2023.02.008. URL https://www.sciencedirect.com/science/article/pii/S0165489623000215.
- D. Cohen and A. Kontorovich. Local Glivenko-Cantelli. In Conference on Learning Theory, Proceedings of Machine Learning Research, 2023a.
- D. Cohen and A. Kontorovich. Open problem: log(n) factor in ”local glivenko-cantelli. In G. Neu and L. Rosasco, editors, The Thirty Sixth Annual Conference on Learning Theory, COLT 2023, 12-15 July 2023, Bangalore, India, volume 195 of Proceedings of Machine Learning Research, pages 5934–5936. PMLR, 2023b. URL https://proceedings.mlr.press/v195/cohen23b.html.
- Sub-Gaussian mean estimators. The Annals of Statistics, 44(6):2695 – 2725, 2016. doi: 10.1214/16-AOS1440. URL https://doi.org/10.1214/16-AOS1440.
- Outlier robust mean estimation with subgaussian rates via stability. Advances in Neural Information Processing Systems, 33:1830–1840, 2020.
- D. Dubhashi and D. Ranjan. Balls and bins: a study in negative dependence. Random Struct. Algorithms, 13(2):99–124, Sept. 1998. ISSN 1042-9832. doi: 10.1002/(SICI)1098-2418(199809)13:2¡99::AID-RSA1¿3.0.CO;2-M. URL http://dx.doi.org/10.1002/(SICI)1098-2418(199809)13:2<99::AID-RSA1>3.0.CO;2-M.
- S. B. Hopkins. Mean estimation with sub-gaussian rates in polynomial time. 2020.
- K. Joag-Dev and F. Proschan. Negative Association of Random Variables with Applications. The Annals of Statistics, 11(1):286 – 295, 1983. doi: 10.1214/aos/1176346079. URL https://doi.org/10.1214/aos/1176346079.
- I. Kaplansky. Set Theory and Metric Spaces. AMS Chelsea Publishing Series. AMS Chelsea Publishing, 2001. ISBN 9780821826942. URL https://books.google.co.il/books?id=FbKhAQAAQBAJ.
- J. C. Lee and P. Valiant. Optimal sub-gaussian mean estimation in ℝℝ\mathbb{R}blackboard_R. In 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS), pages 672–683, 2022. doi: 10.1109/FOCS52979.2021.00071.
- G. Lugosi and S. Mendelson. Sub-Gaussian estimators of the mean of a random vector. The Annals of Statistics, 47(2):783 – 794, 2019a. doi: 10.1214/17-AOS1639. URL https://doi.org/10.1214/17-AOS1639.
- G. Lugosi and S. Mendelson. Mean estimation and regression under heavy-tailed distributions: A survey. Found. Comput. Math., 19(5):1145–1190, 2019b. doi: 10.1007/s10208-019-09427-x. URL https://doi.org/10.1007/s10208-019-09427-x.
- G. Lugosi and S. Mendelson. Robust multivariate mean estimation: The optimality of trimmed mean. The Annals of Statistics, 49(1):393 – 410, 2021. doi: 10.1214/20-AOS1961. URL https://doi.org/10.1214/20-AOS1961.
- Thomas. Is uniform convergence faster for low-entropy distributions? Theoretical Computer Science Stack Exchange, 2018. URL https://cstheory.stackexchange.com/q/42009. URL:https://cstheory.stackexchange.com/q/42009 (version: 2018-12-10).
- R. Van Handel. Probability in high dimension. Technical report, PRINCETON UNIV NJ, 2014.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.