Abstract
We study the properties of ridge functions \(f(x)=g(a\cdot x)\) in high dimensions \(d\) from the viewpoint of approximation theory. The function classes considered consist of ridge functions such that the profile \(g\) is a member of a univariate Lipschitz class with smoothness \(\alpha >0\) (including infinite smoothness) and the ridge direction \(a\) has \(p\)-norm \(\Vert a\Vert _p\le 1\). First, we investigate entropy numbers in order to quantify the compactness of these ridge function classes in \(L_{\infty }\). We show that they are essentially as compact as the class of univariate Lipschitz functions. Second, we examine sampling numbers and consider two extreme cases. In the case \(p=2\), sampling ridge functions on the Euclidean unit ball suffers from the curse of dimensionality. Moreover, it is as difficult as sampling general multivariate Lipschitz functions, which is in sharp contrast to the result on entropy numbers. When we additionally assume that all feasible profiles have a first derivative uniformly bounded away from zero at the origin, the complexity of sampling ridge functions reduces drastically to the complexity of sampling univariate Lipschitz functions. In between, the sampling problem’s degree of difficulty varies, depending on the values of \(\alpha \) and \(p\). Surprisingly, we see almost the entire hierarchy of tractability levels as introduced in the recent monographs by Novak and Woźniakowski.
Similar content being viewed by others
References
Bühlmann, P., van de Geer, S.: Statistics for High-Dimensional Data. Springer, Heidelberg (2011)
Buhmann, M.D., Pinkus, A.: Identifying linear combinations of ridge functions. Adv. Appl. Math. 22, 103–118 (1999)
Candés, E.J.: Harmonic analysis of neural networks. Appl. Comput. Harmon. Anal. 6, 197–218 (1999)
Candés, E.J., Donoho, D.L.: Ridgelets: a key to higher-dimensional intermittency? Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci. 357, 2495–2509 (1999)
Carl, B., Stefani, I.: Entropy, Compactness and the Approximation of Operators. Cambridge Tracts in Mathematics, vol. 98. Cambridge University Press, Cambridge (1990)
Cohen, A., Daubechies, I., DeVore, R.A., Kerkyacharian, G., Picard, D.: Capturing ridge functions in high dimensions from point queries. Constr. Approx. 35, 225–243 (2012)
Creutzig, J., Dereich, S., Müller-Kronbach, T., Ritter, K.: Infinite-dimensional quadrature and approximation of distributions. Found. Comput. Math. 9, 391–429 (2009)
Cucker, F., Zhou, D.-X.: Learning theory: an approximation theory viewpoint. Cambridge Monographs on Applied and Computational Mathematics, vol. 24. Cambridge University Press, Cambridge (2007)
DeVore, R.A., Lorentz, G.G.: Constructive Approximation. Springer, Berlin (1993)
Edmunds, D.E., Triebel, H.: Function Spaces, Entropy Numbers, Differential Operators. Cambridge Tracts in Mathematics, vol. 120. Cambridge University Press, Cambridge (1996)
Flad, H.J., Hackbusch, W., Khoromskij, B.N., Schneider, R.: Concepts of data-sparse tensor-product approximation in many-particle modeling. In: Olshevsky, V., Tyrtyshnikov, E. (eds.) Matrix Methods: Theory, Algorithms and Applications. World Scientific, Singapore (2010)
Fornasier, M., Schnass, K., Vybíral, J.: Learning functions of few arbitrary linear parameters in high dimensions. Found. Comput. Math. 12, 229–262 (2012)
Foucart, S., Pajor, A., Rauhut, H., Ullrich, T.: The Gelfand widths of lp-balls for \(0 < p\le 1\). J. Complexity 26, 629–640 (2010)
Friedman, J.H., Stuetzle, W.: Projection pursuit regression. J. Am. Stat. Assoc. 76, 817–823 (1981)
Golubev, G.K.: Asymptotically minimax estimation of a regression function in an additive model. Problemy Peredachi Informatsii 28, 101–112 (1992)
Graham, R., Sloane, N.: Lower bounds for constant weight codes. IEEE Trans. Inform. Theory 26, 37–43 (1980)
Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning. Springer, New York (2001)
Hinrichs, A., Mayer, S.: Entropy numbers of spheres in Banach and quasi-Banach spaces. University of Bonn, preprint
Hinrichs, A., Novak, E., Ullrich, M., Woźniakowski, H.: The curse of dimensionality for numerical integration of smooth functions II. J. Complex. 30, 117–143 (2014)
Hristache, M., Juditsky, A., Spokoiny, V.: Direct estimation of the index coefficient in a single-index model. Ann. Stat. 29, 595–623 (2001)
Kühn, T.: A lower estimate for entropy numbers. J. Approx. Theory 110, 120–124 (2001)
Logan, B.P., Shepp, L.A.: Optimal reconstruction of a function from its projections. Duke Math. J. 42, 645–659 (1975)
Lorentz, G., von Golitschek, M., Makovoz, Y.: Constructive Approximation: Advanced Problems. Volume 304 of Grundlehren der Mathematischen Wissenschaften, Springer, Berlin (1996)
Maiorov, V.: Geometric properties of the ridge manifold. Adv. Comput. Math. 32, 239–253 (2010)
Novak, E., Triebel, H.: Function spaces in Lipschitz domains and optimal rates of convergence for sampling. Constr. Approx. 23, 325–350 (2006)
Novak, E., Woźniakowski, H.: Tractability of Multivariate Problems, Volume I: Linear Information. EMS Tracts in Mathematics, vol. 6, Eur. Math. Soc. Publ. House, Zürich (2008)
Novak, E., Woźniakowski, H.: Approximation of infinitely differentiable multivariate functions is intractable. J. Complex. 25, 398–404 (2009)
Novak, E., Woźniakowski, H.: Tractability of Multivariate Problems, Volume II: Standard Information for Functionals. EMS Tracts in Mathematics, vol. 12, Eur. Math. Soc. Publ. House, Zürich (2010)
Paskov, S., Traub, J.: Faster evaluation of financial derivatives. J. Portf. Manag. 22, 113–120 (1995)
Pinkus, A.: Approximating by ridge functions. In: Le Méhauté, A., Rabut, C., Schumaker, L.L. (eds.) Surface Fitting and Multiresolution Methods, pp. 279–292. Vanderbilt University Press, Nashville (1997)
Pinkus, A.: Approximation theory of the MLP model in neural networks. Acta Numerica 8, 143–195 (1999)
Raskutti, G., Wainwright, M.J., Yu, B.: Minimax-optimal rates for sparse additive models over kernel classes via convex programming. J. Mach. Learn. Res. 13, 389–427 (2012)
Schütt, C.: Entropy numbers of diagonal operators between symmetric Banach spaces. J. Approx. Theory 40, 121–128 (1984)
Schwab, C., Gittelson, C.J.: Sparse tensor discretizations of high-dimensional parametric and stochastic PDEs. Acta Numerica 20, 291–467 (2011)
Traub, J., Wasilkowski, G., Woźniakowski, H.: Information-Based Complexity. Academic Press, New York (1988)
Triebel, H.: Fractals and Spectra. Birkhäuser, Basel (1997)
Tyagi, H., Cevher, V.: Active learning of multi-index function models. In: Bartlett, P., Pereira, F.C.N., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1475–1483. Curran Associates, Red Hook (2012)
Vybíral, J.: Weak and quasi-polynomial tractability of approximation of infinitely differentiable functions. J. Complex. 30, 48–55 (2014)
Acknowledgments
The authors would like to thank Aicke Hinrichs, Erich Novak, and Mario Ullrich for pointing out relations to the paper [19], as well as Sjoerd Dirksen, Thomas Kühn, and Winfried Sickel for useful comments and discussions. The last author acknowledges the support by the DFG Research Center Matheon “Mathematics for key technologies” in Berlin. The last author was supported by the ERC CZ grant LL1203 of the Czech Ministry of Education.
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by Allan Pinkus.
Rights and permissions
About this article
Cite this article
Mayer, S., Ullrich, T. & Vybíral, J. Entropy and Sampling Numbers of Classes of Ridge Functions. Constr Approx 42, 231–264 (2015). https://doi.org/10.1007/s00365-014-9267-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00365-014-9267-x
Keywords
- Ridge functions
- Sampling numbers
- Entropy numbers
- Rate of convergence
- Information-based complexity
- Curse of dimensionality