# American Institute of Mathematical Sciences

2020, 2(3): 279-307. doi: 10.3934/fods.2020013

## Probabilistic learning on manifolds

 1 Université Gustave Eiffel, Laboratoire Modélisation et Simulation Multi-Echelle, MSME UMR 8208 CNRS, 5 bd Descartes, 77454 Marne-la-Vallée, France 2 University of Southern California, Viterbi School of Engineering, 210 KAP Hall, Los Angeles, CA 90089, USA

* Corresponding author: Christian Soize

Published   2020 Early access  August 2020

This paper presents novel mathematical results in support of the probabilistic learning on manifolds (PLoM) recently introduced by the authors. An initial dataset, constituted of a small number of points given in an Euclidean space, is given. The points are independent realizations of a vector-valued random variable for which its non-Gaussian probability measure is unknown but is, a priori, concentrated in an unknown subset of the Euclidean space. A learned dataset, constituted of additional realizations, is constructed. A transport of the probability measure estimated with the initial dataset is done through a linear transformation constructed using a reduced-order diffusion-maps basis. It is proven that this transported measure is a marginal distribution of the invariant measure of a reduced-order Itô stochastic differential equation. The concentration of the probability measure is preserved. This property is shown by analyzing a distance between the random matrix constructed with the PLoM and the matrix representing the initial dataset, as a function of the dimension of the basis. It is further proven that this distance has a minimum for a dimension of the reduced-order diffusion-maps basis that is strictly smaller than the number of points in the initial dataset.

Citation: Christian Soize, Roger Ghanem. Probabilistic learning on manifolds. Foundations of Data Science, 2020, 2 (3) : 279-307. doi: 10.3934/fods.2020013
##### References:

show all references

##### References:
Left figure: for $\varepsilon_ {\hbox{DM}} = \varepsilon_ {\hbox{opt}}$, distribution of the eigenvalues $\lambda_\alpha(\varepsilon_ {\hbox{opt}})$ in log scale as a function of rank $\alpha$. Right figure: graph of function $m\mapsto \varepsilon_d(m)$
Left figure: distribution of the eigenvalues $\lambda_\alpha(\varepsilon_ {\hbox{opt}})$ in log scale as a function of rank $\alpha\leq 50$ for $\varepsilon_ {\hbox{DM}} = \varepsilon_ {\hbox{opt}} = 60$. Right figure: graph of function $m\mapsto \varepsilon_d(m)$ for $m\leq 50$
Left figure: graph of function $m \mapsto f_d(m)$. Right figure: graph of function $m\mapsto \underline g(m)$
Left figure: graph of function $m \mapsto d_N^{2, {\hbox{sim}}}(m)$. Right figure: graph of function $m \mapsto d_N^{2, {\hbox{sim}}}(m)$ (blue dashed line), and for $m\geq m_ {\hbox{opt}}$, graphs of $m \mapsto d_N^{2,c}(m)$ (dark thick straight line) and $m \mapsto d_N^{2, {\hbox{app}}}(m)$ (red thick curve line)
 [1] Marc Bocquet, Julien Brajard, Alberto Carrassi, Laurent Bertino. Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization. Foundations of Data Science, 2020, 2 (1) : 55-80. doi: 10.3934/fods.2020004 [2] Ning Zhang, Qiang Wu. Online learning for supervised dimension reduction. Mathematical Foundations of Computing, 2019, 2 (2) : 95-106. doi: 10.3934/mfc.2019008 [3] Jiang Xie, Junfu Xu, Celine Nie, Qing Nie. Machine learning of swimming data via wisdom of crowd and regression analysis. Mathematical Biosciences & Engineering, 2017, 14 (2) : 511-527. doi: 10.3934/mbe.2017031 [4] Andreas Chirstmann, Qiang Wu, Ding-Xuan Zhou. Preface to the special issue on analysis in machine learning and data science. Communications on Pure & Applied Analysis, 2020, 19 (8) : i-iii. doi: 10.3934/cpaa.2020171 [5] Mikhail Langovoy, Akhilesh Gotmare, Martin Jaggi. Unsupervised robust nonparametric learning of hidden community properties. Mathematical Foundations of Computing, 2019, 2 (2) : 127-147. doi: 10.3934/mfc.2019010 [6] Mauro Maggioni, James M. Murphy. Learning by active nonlinear diffusion. Foundations of Data Science, 2019, 1 (3) : 271-291. doi: 10.3934/fods.2019012 [7] Émilie Chouzenoux, Henri Gérard, Jean-Christophe Pesquet. General risk measures for robust machine learning. Foundations of Data Science, 2019, 1 (3) : 249-269. doi: 10.3934/fods.2019011 [8] Ana Rita Nogueira, João Gama, Carlos Abreu Ferreira. Causal discovery in machine learning: Theories and applications. Journal of Dynamics & Games, 2021, 8 (3) : 203-231. doi: 10.3934/jdg.2021008 [9] Wenxiong Chen, Congming Li. Harmonic maps on complete manifolds. Discrete & Continuous Dynamical Systems, 1999, 5 (4) : 799-804. doi: 10.3934/dcds.1999.5.799 [10] Ruilin Li, Xin Wang, Hongyuan Zha, Molei Tao. Improving sampling accuracy of stochastic gradient MCMC methods via non-uniform subsampling of gradients. Discrete & Continuous Dynamical Systems - S, 2021  doi: 10.3934/dcdss.2021157 [11] Prashant Shekhar, Abani Patra. Hierarchical approximations for data reduction and learning at multiple scales. Foundations of Data Science, 2020, 2 (2) : 123-154. doi: 10.3934/fods.2020008 [12] Mingbao Cheng, Shuxian Xiao, Guosheng Liu. Single-machine rescheduling problems with learning effect under disruptions. Journal of Industrial & Management Optimization, 2018, 14 (3) : 967-980. doi: 10.3934/jimo.2017085 [13] Hao Li, Honglin Chen, Matt Haberland, Andrea L. Bertozzi, P. Jeffrey Brantingham. PDEs on graphs for semi-supervised learning applied to first-person activity recognition in body-worn video. Discrete & Continuous Dynamical Systems, 2021, 41 (9) : 4351-4373. doi: 10.3934/dcds.2021039 [14] Anja Randecker, Giulio Tiozzo. Cusp excursion in hyperbolic manifolds and singularity of harmonic measure. Journal of Modern Dynamics, 2021, 17: 183-211. doi: 10.3934/jmd.2021006 [15] Miguel A. Dumett, Roberto Cominetti. On the stability of an adaptive learning dynamics in traffic games. Journal of Dynamics & Games, 2018, 5 (4) : 265-282. doi: 10.3934/jdg.2018017 [16] Fei Liu, Jaume Llibre, Xiang Zhang. Heteroclinic orbits for a class of Hamiltonian systems on Riemannian manifolds. Discrete & Continuous Dynamical Systems, 2011, 29 (3) : 1097-1111. doi: 10.3934/dcds.2011.29.1097 [17] Tieliang Gong, Qian Zhao, Deyu Meng, Zongben Xu. Why curriculum learning & self-paced learning work in big/noisy data: A theoretical perspective. Big Data & Information Analytics, 2016, 1 (1) : 111-127. doi: 10.3934/bdia.2016.1.111 [18] Thiago Ferraiol, Mauro Patrão, Lucas Seco. Jordan decomposition and dynamics on flag manifolds. Discrete & Continuous Dynamical Systems, 2010, 26 (3) : 923-947. doi: 10.3934/dcds.2010.26.923 [19] Eugen Mihailescu, Mariusz Urbański. Holomorphic maps for which the unstable manifolds depend on prehistories. Discrete & Continuous Dynamical Systems, 2003, 9 (2) : 443-450. doi: 10.3934/dcds.2003.9.443 [20] Robert L. Peach, Alexis Arnaudon, Mauricio Barahona. Semi-supervised classification on graphs using explicit diffusion dynamics. Foundations of Data Science, 2020, 2 (1) : 19-33. doi: 10.3934/fods.2020002

Impact Factor:

## Tools

Article outline

Figures and Tables