Abstract
By way of concrete presentations, we construct two infinite-dimensional transforms at the crossroads of Gaussian fields and reproducing kernel Hilbert spaces (RKHS), thus leading to a new infinite-dimensional Fourier transform in a general setting of Gaussian processes. Our results serve to unify existing tools from infinite-dimensional analysis.
Similar content being viewed by others
References
Albeverio, S., De Vecchi, F.C., Gubinelli, M.: The elliptic stochastic quantization of some two dimensional Euclidean QFTs. Ann. Inst. Henri Poincaré Probab. Stat. 57(4), 2372–2414 (2021) (MR 4415393)
Albeverio, S., De Vecchi, F.C., Romano, A., Ugolini, S.: Mean-field limit for a class of stochastic ergodic control problems. SIAM J. Control Optim. 60(1), 479–504 (2022). (MR 4379621)
Alaíz, C.M., Fanuel, M., Suykens, J.A.K.: Convex formulation for kernel PCA and its use in semisupervised learning. IEEE Trans. Neural Netw. Learn. Syst. 29(8), 3863–3869 (2018). (MR 3854652)
Alpay, D., Jorgensen, P.E.T.: Stochastic processes induced by singular operators. Numer. Funct. Anal. Optim. 33(7–9), 708–735 (2012). (MR 2966130)
Albeverio, S., Kagawa, T., Yahagi, Y., Yoshida, M.W.: Non-local Markovian symmetric forms on infinite dimensional spaces I. The closability and quasi-regularity. Commun. Math. Phys. 388(2), 659–706 (2021). (MR 4334244)
Amini, A.A., Wainwright, M.J.: Sampled forms of functional PCA in reproducing kernel Hilbert spaces. Ann. Stat. 40(5), 2483–2510 (2012). (MR 3097610)
Bishop, C.M.: Pattern Recognition and Machine Learning, Information Science and Statistics. Springer, New York (2006). (MR 2247587)
Bishop, C.M.: Model-based machine learning. Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 371(1984), 20120222 (2013). (MR 3005666)
Berlinet, A., Thomas-Agnan, C.: Reproducing Kernel Hilbert Spaces in Probability and Statistics. Kluwer Academic Publishers, Boston (2004). (With a preface by Persi Diaconis. MR 2239907)
Coleman, K.D., Lewis, A., Smith, R.C., Williams, B., Morris, M., Khuwaileh, B.: Gradient-free construction of active subspaces for dimension reduction in complex models with applications to neutronics. SIAM/ASA J. Uncertain. Quantif. 7(1), 117–142 (2019). (MR 3900802)
Chui, C.K., Lin, S.-B., Bo, Z., Zhou, D.-X.: Realization of spatial sparseness by deep ReLU nets with massive data. IEEE Trans. Neural Netw. Learn. Syst. 33(1), 229–243 (2022). (MR 4367288)
Dong, J.J., Wang, L., Gill, J., Cao, J.: Functional principal component analysis of glomerular filtration rate curves after kidney transplant. Stat. Methods Med. Res. 27(12), 3785–3796 (2018). (MR 3878657)
Gonen, A., Gilad-Bachrach, R.: Smooth sensitivity based approach for differentially private principal component analysis. Algorithmic learning theory 2018, Proc. Mach. Learn. Res. (PMLR), vol. 83, Proceedings of Machine Learning Research PMLR, pp. 13 (2018) (MR 3857315)
Gupta, M.R., Jacobson, N.P.: Wavelet principal component analysis and its application to hyperspectral images. International Conference on Image Processing, Oct 2006, pp. 1585–1588 (2006)
Grigo, C., Koutsourelakis, P.-S.: Bayesian model and dimension reduction for uncertainty propagation: applications in random media. SIAM/ASA J. Uncertain. Quantif. 7(1), 292–323 (2019). (MR 3922239)
Hida, T.: Brownian Motion, Applications of Mathematics, vol. 11, p. 562914. Springer, New York (1980)(Translated from the Japanese by the author and T, . P. Speed, MR)
Herr, J.E., Jorgensen, P.E.T., Weber, E.S.: A matrix characterization of boundary representations of positive matrices in the Hardy space. Frames and harmonic analysis, Contemp. Math., vol. 706, pp. 255–270. American Mathematical Society (2018) (MR 3796641)
Herr, J.E., Jorgensen, P.E.T., Weber, E.S.: Positive matrices in the Hardy space with prescribed boundary representations via the Kaczmarz algorithm. J. Anal. Math. 138(1), 209–234 (2019). (MR 3996038)
Hu, T., Wu, Q., Zhou, D.-X.: Distributed kernel gradient descent algorithm for minimum error entropy principle. Appl. Comput. Harmon. Anal. 49(1), 229–256 (2020). (MR 4091197)
Hu, T., Zhou, D.-X.: Distributed regularized least squares with flexible Gaussian kernels. Appl. Comput. Harmon. Anal. 53, 349–377 (2021). (MR 4241215)
Janson, S.: Gaussian Hilbert Spaces, Cambridge Tracts in Mathematics, vol. 129. Cambridge University Press, Cambridge (1997). (MR 1474726)
Jin, J., Huang, T., Zheng, J.L., Wen, P.H.: Dimension reduction analysis with mapping and direct integration algorithm. Eng. Anal. Bound. Elem. 99, 122–130 (2019). (MR 3883202)
Jorgensen, P.E.T., Sooran, K., Myung-Sin, S., Feng, T.: Dimension reduction and kernel principal component analysis (2019)
Jorgensen, P.E.T., Song, M.-S.: Entropy encoding, Hilbert space, and Karhunen-Loève transforms. J. Math. Phys. 48(10), 103503 (2007)
Jorgensen, P.E.T., Song, M.-S.: Infinite-dimensional measure spaces and frame analysis. Acta Appl. Math. 155, 41–56 (2018). (MR 3800275)
Jorgensen, P.E.T., Myung-Sin, S., Feng, T.: Positive definite kernels, algorithms, frames, and approximations (2021)
Jorgensen, P., Tian, F.: Realizations and factorizations of positive definite kernels. J. Theor. Probab. 32(4), 1925–1942 (2019). (MR 4020693)
Jorgensen, P., Tian, J.: Decomposition of gaussian processes, and factorization of positive definite kernels. Opuscula Math. 39(4), 497–541 (2019). (MR 3843552)
Jorgensen, P.E.T., Tian, F.: Random Measures in Infinite-dimensional Dynamics, Advanced Topics in Mathematical Analysis, pp. 1–38. CRC Press, Boca Raton (2019). (MR 3888850)
Lee, Y., Hirakawa, K., Nguyen, T.Q.: Camera-aware multi-resolution analysis for raw image sensor data compression. IEEE Trans. Image Process. 27(6), 2806–2817 (2018). (MR 3780557)
Lin, X., Li, R., Yan, F., Lu, T., Huang, X.: Quantile residual lifetime regression with functional principal component analysis of longitudinal data for dynamic prediction. Stat. Methods Med. Res. 28(4), 1216–1229 (2019). (MR 3934645)
Mendelson, S., Milman, E., Paouris, G.: Generalized dual Sudakov minoration via dimension-reduction—a program. Stud. Math. 244(2), 159–202 (2019). (MR 3850675)
Mania, H., Ramdas, A., Wainwright, M.J., Jordan, M.I., Recht, B.: On kernel methods for covariates that are rankings. Electron. J. Stat. 12(2), 2537–2577 (2018). (MR 3843387)
Parthasarathy, K.R., Schmidt, K.: Stable positive definite functions. Trans. Am. Math. Soc. 203, 161–174 (1975). (MR 0370681 (51 #6907))
Raja, S.P.: Secured medical image compression using DES encryption technique in Bandelet multiscale transform. Int. J. Wavelets Multiresolut. Inf. Process. 16(4), 1850028 (2018). (MR 3820672)
Ryabko, B.Y., Sharova, M.P.: Fast encoding of low-entropy sources. Probl. Peredachi Inf. 35(1), 49–60 (1999). (MR 1720704)
Song, M.-S.: Entropy encoding in wavelet image compression, Representations, wavelets, and frames. Appl. Numer. Harmon. Anal. Chapter 14: 293–311 (2008) (MR 2459323)
Smale, S., Zhou, D.-X.: Shannon sampling. II. Connections to learning theory. Appl. Comput. Harmon. Anal. 19(3), 285–302 (2005). (MR 2186447)
Smale, S., Zhou, D.-X.: Learning theory estimates via integral operators and their approximations. Constr. Approx. 26(2), 153–172 (2007). (MR 2327597)
Smale, S., Zhou, D.-X.: Geometry on probability spaces. Constr. Approx. 30(3), 311–323 (2009). (MR 2558684)
Tu, I.-P., Huang, S.-Y., Hsieh, D.-N.: The generalized degrees of freedom of multilinear principal component analysis. J. Multivariate Anal. 173, 26–37 (2019). (MR 3913046)
Vo, H.X., Durlofsky, L.J.: Regularized kernel PCA for the efficient parameterization of complex geological models. J. Comput. Phys. 322, 859–881 (2016). (MR 3534893)
Vakhania, N.N., Tarieladze, V.I., Chobanyan, S.A., Probability Distributions on Banach Spaces, Mathematics and its Applications (Soviet Series), vol. 14. D. Reidel Publishing Co., Dordrecht (1987) (Translated from the Russian and with a preface by Wojbor A, p. 1435288. Woyczynski, MR)
Wang, N., Ge, S., Li, B., Peng, L.: Multiple description image compression based on multiwavelets. Int. J. Wavelets Multiresolut. Inf. Process. 17(1), 1850063 (2019). (MR 3911884)
Yu, Z., Ho, D.W.C., Shi, Z., Zhou, D.-X.: Robust kernel-based distribution regression. Inverse Probl. 37(10), 105014 (2021). (MR 4321422)
Zwald, L., Bousquet, O., Blanchard, G.: Statistical Properties of Kernel Principal Component Analysis, Learning theory, Lecture Notes in Computer Science, vol. 3120, pp. 594–608. Springer, Berlin (2004). (MR 2177937)
Acknowledgements
The co-authors thank the following colleagues for helpful and enlightening discussions: Professors Daniel Alpay, Sergii Bezuglyi, Ilwoo Cho, Wayne Polyzou, David Stewart, Eric S. Weber, and members in the Math Physics seminar at The University of Iowa.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors did not receive support from any organization for the submitted work. The authors have no relevant financial or non-financial interests to disclose. Palle Jorgensen, Myung-Sin Song, James Tian.
Additional information
Communicated by Laura De Carli.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Jorgensen, P.E.T., Song, MS. & Tian, J. Infinite-dimensional stochastic transforms and reproducing kernel Hilbert space. Sampl. Theory Signal Process. Data Anal. 21, 12 (2023). https://doi.org/10.1007/s43670-023-00051-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s43670-023-00051-z
Keywords
- Positive-definite kernels
- Fourier analysis
- Probability
- Stochastic processes
- Reproducing kernel Hilbert space
- Complex function-theory
- Interpolation
- Signal/image processing
- Sampling
- Frames
- Moments
- Machine learning
- Embedding problems
- Geometry
- Information theory
- Optimization
- Algorithms
- Kaczmarz
- Karhunen–Loève
- Factorizations
- Splines
- Principal Component Analysis
- Dimension reduction
- Digital image analysis
- Covariance matrix
- Gaussian process
- Mathematical physics