Papers
Topics
Authors
Recent
Search
2000 character limit reached

Breuer-Major Theorems for Hilbert Space-Valued Random Variables

Published 19 May 2024 in math.PR, math.ST, and stat.TH | (2405.11452v1)

Abstract: Let ${X_k}{k \in \mathbb{Z}}$ be a stationary Gaussian process with values in a separable Hilbert space $\mathcal{H}_1$, and let $G:\mathcal{H}_1 \to \mathcal{H}_2$ be an operator acting on $X_k$. Under suitable conditions on the operator $G$ and the temporal and cross-sectional correlations of ${X_k}{k \in \mathbb{Z}}$, we derive a central limit theorem (CLT) for the normalized partial sums of ${G[X_k]}{k \in \mathbb{Z}}$. To prove a CLT for the Hilbert space-valued process ${G[X_k]}{k \in \mathbb{Z}}$, we employ techniques from the recently developed infinite dimensional Malliavin-Stein framework. In addition, we provide quantitative and continuous time versions of the derived CLT. In a series of examples, we recover and strengthen limit theorems for a wide array of statistics relevant in functional data analysis, and present a novel limit theorem in the framework of neural operators as an application of our result.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Arcones, M. Limit theorems for nonlinear functionals of a stationary Gaussian sequence of vectors. The Annals of Probability 22, 4 (1994), 2242–2274.
  2. On the prediction of stationary functional time series. Journal of the American Statistical Association 110, 509 (2015), 378–392.
  3. Multivariate limit theorems in the context of long-range dependence. Journal of Time Series Analysis 34, 6 (2013), 717–743.
  4. Non-asymptotic approximations of Gaussian neural networks via second-order Poincaré inequalities. arXiv preprint arXiv:2304.04010 (2023).
  5. Bosq, D. Linear Processes in Function Spaces: Theory and Applications. Springer-Verlag, New York, 2000.
  6. Approximation of Hilbert-valued Gaussians on Dirichlet structures. Electronic Journal of Probability 25 (2020), 1–30.
  7. Central limit theorems for non-linear functionals of Gaussian fields. Journal of Multivariate Analysis 13, 3 (1983), 425–441.
  8. Continuous Breuer-Major theorem: Tightness and non-stationarity. The Annals of Probability 48, 1 (2020), 147–177.
  9. Cartan, H. Differential Forms. Dover Publications, New York, 1970. Translated from the French.
  10. Da Prato, G. An Introduction to Infinite-Dimensional Analysis. Springer-Verlag, Berlin, 2006.
  11. The conditional central limit theorem in Hilbert spaces. Stochastic Processes and their Applications 108, 2 (2003), 229–262.
  12. Düker, M. Limit theorems for Hilbert space-valued linear processes under long-range dependence. Stochastic Processes and their Applications 128, 5 (2018), 1439–1465.
  13. Düker, M. Sample autocovariance operators of long-range dependent Hilbert space-valued linear processes. Preprint (2020).
  14. Quantitative CLTs in deep neural networks. arXiv preprint arXiv:2307.06092 (2023).
  15. On the central limit theorem in Hilbert space. Stochastica 4, 1 (1980), 43–71.
  16. CLT and other limit theorems for functionals of Gaussian processes. Zeitschrift für Wahrscheinlichkeitstheorie und verwandte Gebiete 70, 2 (1985), 191–212.
  17. Limiting distributions of nonlinear vector functions of stationary Gaussian processes. The Annals of Probability 18, 3 (1990), 1159–1173.
  18. Inference for Functional Data with Applications. Springer-Verlag, New York, 2012.
  19. Theoretical Foundations of Functional Data Analysis, with an Introduction to linear operators. Wiley Series in Probability and Statistics. John Wiley & Sons, Chichester, 2015.
  20. Jirak, M. Rate of convergence for Hilbert space valued processes. Bernoulli 24, 1 (2018), 202–230.
  21. Neural operator: Learning maps between function spaces with applications to PDEs. Journal of Machine Learning Research 24, 89 (2023), 1–97.
  22. Rate of convergence in the Breuer-Major theorem via chaos expansions. Stochastic Analysis and Applications 37, 6 (2019), 1057–1091.
  23. Convolutional autoregressive models for functional time series. Journal of Econometrics 194, 2 (2016), 263–282.
  24. Central limit theorem for stationary processes in Hilbert space. Theory of Probability & its Applications 27, 2 (1983), 357–359.
  25. Mas, A. Weak convergence for the covariance operators of a Hilbertian linear process. Stochastic Processes and their Applications 99, 1 (2002), 117–135.
  26. Mas, A. A sufficient condition for the CLT in the space of nuclear operators–application to covariance of random functions. Statistics & Probability Letters 76, 14 (2006), 1503–1509.
  27. Merlevède, F. On the central limit theorem and its weak invariance principle for strongly mixing sequences with values in a Hilbert space via martingale approximation. Journal of Theoretical Probability 16, 3 (2003), 625–653.
  28. Sharp conditions for the CLT of linear processes in a Hilbert space. Journal of Theoretical Probability 10 (1997), 681–693.
  29. Merlevède, F. Central limit theorem for linear processes with values in a Hilbert space. Stochastic Processes and their Applications 65, 1 (1996), 103–114.
  30. Kernel autocovariance operators of stationary processes: Estimation and convergence. Journal of Machine Learning Research 23, 327 (2022), 1–34.
  31. The functional Breuer–Major theorem. Probability Theory and Related Fields 176, 1-2 (2020), 203–218.
  32. The Breuer–Major theorem in total variation: Improved rates under minimal regularity. Stochastic Processes and their Applications 131 (2021), 1–20.
  33. Stein’s method and exact Berry–Esseen asymptotics for functionals of Gaussian fields. The Annals of Probability 37, 6 (2009), 2231–2261.
  34. Normal Approximations with Malliavin Calculus: From Stein’s Method to Universality. Cambridge University Press, 2012.
  35. The optimal fourth moment theorem. Proceedings of the American Mathematical Society 143, 7 (2015), 3123–3133.
  36. Quantitative Breuer-Major theorems. Stochastic Processes and their Applications 121, 4 (2011), 793–812.
  37. Multivariate normal approximation using Stein’s method and Malliavin calculus. Annales de l’IHP Probabilités et Statistiques 46, 1 (2010), 45–58.
  38. Berry-Esseen bounds in the Breuer-Major CLT and Gebelein’s inequality. Electronic Communications in Probability 24, none (2019), 1–12.
  39. Asymptotic independence of multiple Wiener–Itô integrals and the resulting limit laws. The Annals of Probability 42, 2 (2014), 497–526.
  40. Nualart, D. The Malliavin Calculus and Related Topics. Springer-Verlag, Berlin, 2006.
  41. Wiener Chaos: Moments, Cumulants and Diagrams: A Survey with Computer Implementation. Springer-Verlag, Milan, 2011.
  42. Long-Range Dependence and Self-Similarity. Cambridge University Press, 2017.
  43. Functional Data Analysis. Springer-Verlag, New York, 1997.
  44. Varadhan, S. Limit theorems for sums of independent random variables with values in a Hilbert space. Sankhyā: The Indian Journal of Statistics, Series A 24, 3 (1962), 213–238.
  45. Functional autoregressive processes in reproducing kernel Hilbert spaces. arXiv preprint arXiv:2011.13993 (2020).

Summary

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.

Collections

Sign up for free to add this paper to one or more collections.

Tweets

Sign up for free to view the 2 tweets with 0 likes about this paper.