Abstract
We consider the problem of the uniform (in \(L_\infty \)) recovery of ridge functions \(f(x)=\varphi (\langle a,x\rangle )\), \(x\in B_2^n\), using noisy evaluations \(y_1\approx f(x^1),\ldots ,y_N\approx f(x^N)\). It is known that for classes of functions \(\varphi \) of finite smoothness the problem suffers from the curse of dimensionality: in order to provide good accuracy for the recovery it is necessary to make exponential number of evaluations. We prove that if \(\varphi \) is analytic in a neighborhood of \([-1,1]\) and the noise is very small, \(\varepsilon \leqslant \exp (-c\log ^2n)\), then there is an efficient algorithm that recovers f with good accuracy using \(O(n\log ^2n)\) function evaluations.
Similar content being viewed by others
References
Bernstein, S.: Sur la meilleure approximation des fonctions continues par les polynomes du degré donné. II. Communications de la Société mathématique de Kharkow, 2-ée série 13, 145–194 (1912). (in Russian)
Buhmann, M.D., Pinkus, A.: Identifying linear combinations of ridge functions. Adv. Appl. Math. 22, 103–118 (1999)
Cohen, A., Daubechies, I., DeVore, R., Kerkyacharian, G., Picard, D.: Capturing ridge functions in high dimensions from point queries. Constr. Approx. 35, 225–243 (2012)
Casazza, P.G., Woodland, L.M.: Phase retrieval by vectors and projections. Operator methods in wavelets, tilings, and frames. Contemp. Math. 626, 1–7 (2014)
Demanet, L., Townsend, A.: Stable extrapolation of analytic functions. Found. Comput. Math. 19, 297–331 (2019)
Doerr, B., Mayer, S.: The recovery of ridge functions on the hypercube suffers from the curse of dimensionality. J. Complex. 63, 101521 (2021)
Dick, J., Kritzer, P., Pillichshammer, F., Wozniakowski, H.: Approximation of analytic functions in Korobov spaces. J. Complex. 30, 2–28 (2014)
Fornasier, M., Schnass, K., Vybiral, J.: Learning functions of few arbitrary linear parameters in high dimensions. Found. Comput. Math. 12, 229–262 (2012)
Gaiffas, S., Lecue, G.: Optimal rates and adaptation in the single-index model using aggregation. Electron. J. Stat. 1, 538–573 (2007)
Khokhlov, V.I.: The uniform distribution on a sphere in ${\mathbb{R}}^s$. Properties of projections. I. Theory Probab. Appl. 50, 386–399 (2006)
Konyagin, S.V., Kuleshov, A.A., Maiorov, V.E.: Some problems in the theory of ridge functions. Proc. Steklov Inst. Math. 301, 144–169 (2018)
Massart, P.: The tight constant in the Dvoretzky–Kiefer–Wolfowitz inequality. Ann. Probab. 18, 1269–1283 (1990)
Mayer, S., Ullrich, T., Vybiral, J.: Entropy and sampling numbers of classes of ridge functions. Constr. Approx. 42, 231–264 (2015)
Natanson, I.P.: Constructive Function Theory, vol. 1. Ungar, New York (1964)
Novak, E., Wozniakowski, H.: Tractability of multivariate problems for standard and linear information in the worst case setting, Part I. J. Approx. Theory 207, 177–192 (2016)
Osipenko, K.Y.: Optimal Recovery of Analytic Functions. Nova Publishers, Hauppauge (2000)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numer. 8, 143–195 (1999)
Pinkus, A.: Ridge Functions. Cambridge Tracts in Mathematics, vol. 205. Cambridge University Press, Cambridge (2015)
Šíma, J.: Training a single sigmoidal neuron is hard. Neural Comput. 14, 2709–2728 (2002)
Temlyakov, V.: Greedy Approximation. Cambridge University Press, Cambridge (2011)
Tyagi, H., Cevher, V.: Learning non-parametric basis independent models from point queries via low-rank methods. Appl. Comput. Harmon. Anal. 37, 389–412 (2014)
Vybíral, J.: Weak and quasi-polynomial tractability of approximation of infinitely differentiable functions. J. Complex. 30, 48–55 (2014)
Zaitseva, T.I., Malykhin, Yu.V., Ryutin, K.S.: On recovery of regular ridge functions. Math. Notes 109, 307–311 (2021)
Acknowledgements
The authors wish to express their gratitude to S.V. Konyagin for his suggestion to consider the case of regular ridge functions and constant encouragement and to the anonymous referees for their careful work and precise comments.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Vladimir N. Temlyakov.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The authors were supported by the Russian Federation Government Grant No. 14.W03.31.0031.
Rights and permissions
About this article
Cite this article
Malykhin, Y., Ryutin, K. & Zaitseva, T. Recovery of Regular Ridge Functions on the Ball. Constr Approx 56, 687–708 (2022). https://doi.org/10.1007/s00365-022-09568-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00365-022-09568-3