Abstract
We consider the problem of constructing upper bounds for the expectation of the norm of a vector uniformly distributed on the Euclidean unit sphere.
Similar content being viewed by others
References
E. Vorontsova, A. Gasnikov, and E. Gorbunov, “Accelerated directional search with non-Euclidean prox-structure,” Automat. Remote Control 80(4), 693–707 (2019).
A. Gasnikov, A. Lagunovskaya, I. Usmanova, and F. Fedorenko, “Gradient-free prox-methods with inexact oracle for stochastic convex optimization problems on a simplex,” Automat. Remote Control 77(11), 2018–2034 (2016).
A. V. Gasnikov, A. A. Lagunovskaya, I. N. Usmanova, and F. A. Fedorenko, “Gradient-free proximal methods with inexact oracle for convex stochastic nonsmooth optimization problems on the simplex,” Avtomat. Telemekh., No. 10, 57–77 (2016) [Automat. Remote Control 77 (11), 2018–2034 (2016)].
O. Shamir, An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback, arXiv: http://arxiv.org/abs/1507.08752 (2015).
O. Shamir, “An optimal algorithm for bandit and zero-order convex optimization with two-point feedback,” J. Mach. Learn. Res. 18, Paper No. 52 (2017).
J. C. Duchi, M. I. Jordan, M. J. Wainwright, and A. Wibisono, “Optimal rates for zero-order convex optimization: The power of two function evaluations,” IEEE Trans. Inform. Theory 61(5), 2788–2806 (2015).
A. Blum, J. Hopcroft, and R. Kannan, Foundations of Data Science, https://www.cs.cornell.edu/jeh/book.pdf (2018).
K. Ball, “An elementary introduction to modern convex geometry,” in Flavors of Geometry, Math. Sci. Res. Inst. Publ. (Cambridge Univ. Press, Cambridge, 1997), Vol. 31.
L. Bogolubsky, P. Dvurechensky, A. Gasnikov, G. Gusev, Yu. Nesterov, A. Raigorodskii, A. Tikhonov, and M. Zhukovskii, Learning Supervised PageRank with Gradient-Based and Gradient-Free Optimization Methods, https://papers.nips.cc/paper/6565-learning-supervised-pagerank-with-gradient-based-and-gradient-free-optimization-methods.pdf (2016).
S. Boucheron, G. Lugosi, and P. Massart, Concentration Inequalities. A Nonasymptotic Theory of Independence (Oxford Univ. Press, Oxford, 2013).
V. Milman and G. Schechtman, Asymptotic Theory of Finite Dimensional Normed Spaces, in Lecture Notes in Math. (Springer-Verlag, Berlin, 1986), Vol. 1200.
V. A. Zorich, Mathematical Analysis in Problems of Natural Science (MTsNMO, Moscow, 2008) [in Russian].
A. Bayandina, A. Gasnikov, and A. Lagunovskaya, “Gradient-free two-point methods for solving stochastic nonsmooth convex optimization problems with small nonrandom noises,” Automat. Remote Control 79(8), 1399–1408 (2018).
M. Lifshits, Lectures on Gaussian Processes (Springer, Heidelberg, 2012).
É. A. Gorbunov and E. A. Vorontsova, Computational Experiments Illustrating the Phenomenon of Concentration of Uniform Measure on the Surface of the Euclidean Sphere in a Small Neighborhood of the Equator, https://github.com/evorontsova/Concentration-of-Measure, 2018 [in Russian].
Acknowledgments
The authors wish to express gratitude to P. E. Dvurechensky for his help.
Funding
The work of A. V. Gasnikov was supported by the Program of the President of the Russian Federation under grant MD-1320.2018.1. The work of È. A. Gorbunov was supported by the Russian Foundation for Basic Research under grant 18-31-20005 mol_a_ved. The work of E. A. Vorontsova was supported by the Russian Foundation for Basic Research under grant 18-29-03071.
Author information
Authors and Affiliations
Corresponding authors
Additional information
Russian Text © The Author(s), 2019, published in Matematicheskie Zametki, 2019, Vol. 106, No. 1, pp. 13–23.
Rights and permissions
About this article
Cite this article
Gorbunov, É.A., Vorontsova, E.A. & Gasnikov, A.V. On the Upper Bound for the Expectation of the Norm of a Vector Uniformly Distributed on the Sphere and the Phenomenon of Concentration of Uniform Measure on the Sphere. Math Notes 106, 11–19 (2019). https://doi.org/10.1134/S0001434619070022
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0001434619070022