Advertisement

Some Problems in the Theory of Ridge Functions

  • S. V. Konyagin
  • A. A. Kuleshov
  • V. E. Maiorov
Article

Abstract

Let d ≥ 2 and \(E\subset\mathbb{R}^d\) be a set. A ridge function on E is a function of the form φ(a · x), where \(x=(x_1,...,x_d)\in{E},\;a=(a_1,...,a_d)\in\mathbb{R}^d\;\backslash\left\{0\right\},\;a \cdot x = \sum\nolimits_{j = 1}^d {{a_j}{x_j}}\), and φ is a real-valued function. Ridge functions play an important role both in approximation theory and mathematical physics and in the solution of applied problems. The present paper is of survey character. It addresses the problems of representation and approximation of multidimensional functions by finite sums of ridge functions. Analogs and generalizations of ridge functions are also considered.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. L. Agranovsky and E. T. Quinto, “Injectivity sets for the Radon transform over circles and complete systems of radial functions,” J. Funct. Anal. 139 (2), 383–414 (1996).MathSciNetzbMATHCrossRefGoogle Scholar
  2. 2.
    R. A. Aliev and V. E. Ismailov, “On a smoothness problem in ridge function representation,” Adv. Appl. Math. 73, 154–169 (2016).MathSciNetzbMATHCrossRefGoogle Scholar
  3. 3.
    V. I. Arnol’d, “On functions of three variables,” Dokl. Akad. Nauk SSSR 114 (4), 679–681 (1957) [Am. Math. Soc. Transl., Ser. 2, 28, 51–54 (1963)].MathSciNetzbMATHGoogle Scholar
  4. 4.
    M.-B. A. Babaev, “Approximation of polynomials in two variables by functions of the form φ(x) + Ψ(y),” Dokl. Akad. Nauk SSSR 193 (5), 967–969 (1970) [Sov. Math., Dokl. 11, 1034–1036 (1970)].MathSciNetGoogle Scholar
  5. 5.
    M.-B. A. Babaev, “Approximation of polynomials in two variables by sums of functions of one variable,” Izv. Akad. Nauk Azerb. SSR, Ser. Fiz.-Tekh. Mat. Nauk, No. 2, 23–29 (1971).zbMATHGoogle Scholar
  6. 6.
    M.-B. A. Babaev, “On obtaining close estimates in the approximation of functions of many variables by sums of functions of a fewer number of variables,” Mat. Zametki 12 (1), 105–114 (1972) [Math. Notes 12, 495–500 (1972)].MathSciNetGoogle Scholar
  7. 7.
    M.-B. A. Babaev, “On the properties of the best approximation function,” Izv. Akad. Nauk Azerb. SSR, Ser. Fiz.-Tekh. Mat. Nauk, No. 3, 20–25 (1972).Google Scholar
  8. 8.
    M.-B. A. Babaev, “Approximation of functions of three variables by sums of functions of two variables,” Soobshch. Akad. Nauk Gruz. SSR 83 (2), 309–312 (1976).MathSciNetGoogle Scholar
  9. 9.
    M.-B. A. Babaev, “Direct theorems for approximation of functions of many variables by sums of functions of a fewer number of variables,” in Special Issues in Function Theory (Elm, Baku, 1980), Issue 2, pp. 3–30 [in Russian].Google Scholar
  10. 10.
    M.-B. A. Babaev, “Extremal elements and the value of the best approximation of a monotone function on Rn by sums of functions of fewer variables,” Dokl. Akad. Nauk SSSR 265 (1), 11–13 (1982) [Sov. Math., Dokl. 26, 1–4 (1982)].MathSciNetGoogle Scholar
  11. 11.
    M.-B. A. Babaev, “Extremal properties and two-sided estimates in approximation by sums of functions of lesser number of variables,” Mat. Zametki 36 (5), 647–659 (1984) [Math. Notes 36, 821–828 (1984)].MathSciNetzbMATHGoogle Scholar
  12. 12.
    M.-B. A. Babaev, “Best approximation by functions of fewer variables,” Dokl. Akad. Nauk SSSR 279 (2), 273–277 (1984) [Sov. Math., Dokl. 30, 629–632 (1984)].MathSciNetzbMATHGoogle Scholar
  13. 13.
    M.-B. A. Babaev, “Estimates of best approximation by quasipolynomials,” in Theory of Functions and Approximations: Proc. 2nd Saratov Winter School, 1984 (Saratov. Univ., Saratov, 1986), Part 1, pp. 91–98 [in Russian].Google Scholar
  14. 14.
    M.-B. A. Babaev, “The approximation of Sobolev classes of functions by sums of products of functions of fewer variables,” Tr. Mat. Inst. im. V.A. Steklova, Akad. Nauk SSSR 180, 30–32 (1987) [Proc. Steklov Inst. Math. 180, 31–33 (1989)].Google Scholar
  15. 15.
    M.-B. A. Babaev, “Best approximation by bilinear forms,” Mat. Zametki 46 (2), 21–33 (1989) [Math. Notes 46, 588–596 (1989)].MathSciNetzbMATHGoogle Scholar
  16. 16.
    M.-B. A. Babaev, “Approximation of Sobolev classes of functions by sums of products of functions of fewer variables,” Mat. Zametki 48 (6), 10–21 (1990) [Math. Notes 48, 1178–1186 (1990)].zbMATHGoogle Scholar
  17. 17.
    M.-B. A. Babaev, “On the degree of approximation of the Sobolev class Wr q by bilinear forms in Lp for 1 = q = p = 2,” Mat. Sb. 182 (1), 122–129 (1991) [Math. USSR, Sb. 72 (1), 113–120 (1992)].Google Scholar
  18. 18.
    A. R. Barron, “Universal approximation bounds for superpositions of a sigmoidal function,” IEEE Trans. Inf. Theory 39 (3), 930–945 (1993).MathSciNetzbMATHCrossRefGoogle Scholar
  19. 19.
    P. L. Bartlett, V. Maiorov, and R. Meir, “Almost linear VC-dimension bounds for piecewise polynomial networks,” Neural Comput. 10 (8), 2159–2173 (1998).CrossRefGoogle Scholar
  20. 20.
    N. Bary, “Mémoire sur la représentation finie des fonctions continues. I: Les superpositions de fonctions absolument continues,” Math. Ann. 103, 185–248 (1930).MathSciNetzbMATHCrossRefGoogle Scholar
  21. 21.
    N. Bary, “Mémoire sur la représentation finie des fonctions continues. II: Le théorème fondamental sur la représentation finie,” Math. Ann. 103, 598–653 (1930).MathSciNetzbMATHCrossRefGoogle Scholar
  22. 22.
    D. Bazarkhanov and V. Temlyakov, “Nonlinear tensor product approximation of functions,” J. Complexity 31 (6), 867–884 (2015).MathSciNetzbMATHCrossRefGoogle Scholar
  23. 23.
    D. Braess and A. Pinkus, “Interpolation by ridge functions,” J. Approx. Theory 73 (2), 218–236 (1993).MathSciNetzbMATHCrossRefGoogle Scholar
  24. 24.
    Yu. A. Brudnyi, “Approximation of functions of n variables by quasipolynomials,” Izv. Akad. Nauk SSSR, Ser. Mat. 34 (3), 564–583 (1970) [Math. USSR, Izv. 4 (3), 568–586 (1970)].MathSciNetGoogle Scholar
  25. 25.
    M. D. Buhmann, “Radial functions on compact support,” Proc. Edinb. Math. Soc., Ser. 2, 41 (1), 33–46 (1998).MathSciNetzbMATHCrossRefGoogle Scholar
  26. 26.
    M. D. Buhmann, “Radial basis functions,” Acta Numerica 9, 1–38 (2000).MathSciNetzbMATHCrossRefGoogle Scholar
  27. 27.
    M. D. Buhmann and A. Pinkus, “Identifying linear combinations of ridge functions,” Adv. Appl. Math. 22 (1), 103–118 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  28. 28.
    E. J. Candès, “Harmonic analysis of neural networks,” Appl. Comput. Harmon. Anal. 6 (2), 197–218 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  29. 29.
    E. J. Candès, “Ridgelets: estimating with ridge functions,” Ann. Stat. 31 (5), 1561–1599 (2003).MathSciNetzbMATHCrossRefGoogle Scholar
  30. 30.
    R. Courant and D. Hilbert, Methoden der mathematischen Physik (J. Springer, Berlin, 1937), Vol.2.Google Scholar
  31. 31.
    C. de Boor, R. A. DeVore, and A. Ron, “Approximation from shift-invariant subspaces of L2(Rd),” Trans. Am. Math. Soc. 341 (2), 787–806 (1994).zbMATHGoogle Scholar
  32. 32.
    N. G. de Bruijn, “Functions whose differences belong to a given class,” Nieuw Arch. Wiskd., Ser. 2, 23, 194–218 (1951).MathSciNetzbMATHGoogle Scholar
  33. 33.
    N. G. de Bruijn, “A difference property for Riemann integrable functions and for some similar classes of functions,” Nederl. Akad. Wet., Proc., Ser. A 55, 145–151 (1952).MathSciNetzbMATHGoogle Scholar
  34. 34.
    R. A. DeVore, K. I. Oskolkov, and P. P. Petrushev, “Approximation by feed-forward neural networks,” Ann. Numer. Math. 4, 261–287 (1997).MathSciNetzbMATHGoogle Scholar
  35. 35.
    S. P. Diliberto and E. G. Straus, “On the approximation of a function of several variables by the sum of functions of fewer variables,” Pac. J. Math. 1, 195–210 (1951).MathSciNetzbMATHCrossRefGoogle Scholar
  36. 36.
    D. L. Donoho and I. M. Johnstone, “Projection-based approximation and a duality with kernel methods,” Ann. Stat. 17 (1), 58–106 (1989).MathSciNetzbMATHCrossRefGoogle Scholar
  37. 37.
    J. Duchon, “Splines minimizing rotation-invariant semi-norms in Sobolev spaces,” in Constructive Theory of Functions of Several Variables: Proc. Conf. Oberwolfach, 1976 (Springer, Berlin, 1977), Lect. Notes Math. 571, pp. 85–100.CrossRefGoogle Scholar
  38. 38.
    N. Dyn, F. J. Narcowich, and J. D. Ward, “Variational principles and Sobolev-type estimates for generalized interpolation on a Riemannian manifold,” Constr. Approx. 15 (2), 175–208 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  39. 39.
    R. E. Edwards, “Spans of translates in Lp(G),” J. Aust. Math. Soc. 5, 216–233 (1965).zbMATHCrossRefGoogle Scholar
  40. 40.
    S. Ellacott and D. Bose, Neural Networks: Deterministic Methods of Analysis (Int. Thomson Comput. Press, London, 1996).Google Scholar
  41. 41.
    J. H. Friedman and W. Stuetzle, “Projection pursuit regression,” J. Am. Stat. Assoc. 76, 817–823 (1981).MathSciNetCrossRefGoogle Scholar
  42. 42.
    A. L. Garkavi, V. A. Medvedev, and S. Ya. Khavinson, “On the existence of a best uniform approximation of a function of several variables by the sum of functions of fewer variables,” Mat. Sb. 187 (5), 3–14 (1996) [Sb. Math. 187, 623–634 (1996)].MathSciNetzbMATHCrossRefGoogle Scholar
  43. 43.
    M. v. Golitschek and W. A. Light, “Approximation by solutions of the planar wave equation,” SIAM J. Numer. Anal. 29 (3), 816–830 (1992).MathSciNetzbMATHCrossRefGoogle Scholar
  44. 44.
    Y. Gordon, V. Maiorov, M. Meyer, and S. Reisner, “On the best approximation by ridge functions in the uniform norm,” Constr. Approx. 18 (1), 61–85 (2002).MathSciNetzbMATHCrossRefGoogle Scholar
  45. 45.
    H. Herrlich, Axiom of Choice (Springer, Berlin, 2006), Lect. Notes Math. 1876.zbMATHGoogle Scholar
  46. 46.
    V. E. Ismailov, “Methods for computing the least deviation from the sums of functions of one variable,” Sib. Mat. Zh. 47 (5), 1076–1082 (2006) [Sib. Math. J. 47, 883–888 (2006)].zbMATHCrossRefGoogle Scholar
  47. 47.
    V. E. Ismailov, “Characterization of an extremal sum of ridge functions,” J. Comput. Appl. Math. 205 (1), 105–115 (2007).MathSciNetzbMATHCrossRefGoogle Scholar
  48. 48.
    V. E. Ismailov, “On the representation by linear superpositions,” J. Approx. Theory 151 (2), 113–125 (2008).MathSciNetzbMATHCrossRefGoogle Scholar
  49. 49.
    V. E. Ismailov, “On the proximinality of ridge functions,” Saraevo J. Math. 5 (1), 109–118 (2009).MathSciNetzbMATHGoogle Scholar
  50. 50.
    V. E. Ismailov, “A review of some results on ridge function approximation,” Azerb. J. Math. 3 (1), 3–51 (2013).MathSciNetzbMATHGoogle Scholar
  51. 51.
    V. E. Ismailov and A. Pinkus, “Interpolation on lines by ridge functions,” J. Approx. Theory 175, 91–113 (2013).MathSciNetzbMATHCrossRefGoogle Scholar
  52. 52.
    Y. Ito and K. Saito, “Superposition of linearly independent functions and finite mappings by neural networks,” Math. Sci. 21 (1), 27–33 (1996).MathSciNetzbMATHGoogle Scholar
  53. 53.
    F. John, Plane Waves and Spherical Means Applied to Partial Differential Equations (Interscience, New York, 1955).zbMATHGoogle Scholar
  54. 54.
    L. K. Jones, “A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training,” Ann. Stat. 20 (1), 608–613 (1992).MathSciNetzbMATHCrossRefGoogle Scholar
  55. 55.
    L. K. Jones, “The computational intractability of training sigmoidal neural networks,” IEEE Trans. Inf. Theory 43 (1), 167–173 (1997).MathSciNetzbMATHCrossRefGoogle Scholar
  56. 56.
    B. S. Kashin, “On some properties of the space of trigonometric polynomials that are related to uniform convergence,” Soobshch. Akad. Nauk Gruz. SSR 93 (2), 281–284 (1979).zbMATHGoogle Scholar
  57. 57.
    S. Ya. Khavinson, “A Chebyshev theorem for the approximation of a function of two variables by sums of the type φ(x) + ψ(y),” Izv. Akad. Nauk SSSR, Ser. Mat. 33 (3), 650–666 (1969) [Math. USSR, Izv. 3 (3), 617–632 (1969)].MathSciNetGoogle Scholar
  58. 58.
    S. Ya. Khavinson, Best Approximation by Linear Superpositions (Approximate Nomography) (Am. Math. Soc., Providence, RI, 1997), Transl. Math. Monogr. 159.zbMATHGoogle Scholar
  59. 59.
    G. M. Khenkin, “Linear superpositions of continuously differentiable functions,” Dokl. Akad. Nauk SSSR 157 (2), 288–290 (1964) [Sov. Math., Dokl. 5, 948–950 (1964)].MathSciNetzbMATHGoogle Scholar
  60. 60.
    A. N. Kolmogorov, “On the representation of continuous functions of several variables by superpositions of continuous functions of a smaller number of variables,” Dokl. Akad. Nauk SSSR 108 (2), 179–182 (1956) [Am. Math. Soc. Transl., Ser. 2, 17, 369–373 (1961)].MathSciNetzbMATHGoogle Scholar
  61. 61.
    A. N. Kolmogorov, “On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition,” Dokl. Akad. Nauk SSSR 114 (5), 953–956 (1957) [Am. Math. Soc. Transl., Ser. 2, 28, 55–59 (1963)].MathSciNetzbMATHGoogle Scholar
  62. 62.
    V. N. Konovalov, K. A. Kopotun, and V. E. Maiorov, “Convex polynomial and ridge approximation of Lipschitz functions in Rd,” Rocky Mt. J. Math. 40 (3), 957–976 (2010).zbMATHCrossRefGoogle Scholar
  63. 63.
    V. N. Konovalov, D. Leviatan, and V. E. Maiorov, “Approximation by polynomials and ridge functions of classes of s-monotone radial functions,” J. Approx. Theory 152 (1), 20–51 (2008).MathSciNetzbMATHCrossRefGoogle Scholar
  64. 64.
    V. N. Konovalov, D. Leviatan, and V. E. Maiorov, “Approximation of Sobolev classes by polynomials and ridge functions,” J. Approx. Theory 159 (1), 97–108 (2009).MathSciNetzbMATHCrossRefGoogle Scholar
  65. 65.
    V. N. Konovalov and V. E. Maiorov, “Widths of some classes of convex functions and bodies,” Izv. Ross. Akad. Nauk, Ser. Mat. 74 (1), 135–158 (2010) [Izv. Math. 74, 127–150 (2010)].MathSciNetzbMATHCrossRefGoogle Scholar
  66. 66.
    S. V. Konyagin and A. A. Kuleshov, “On the continuity of finite sums of ridge functions,” Mat. Zametki 98 (2), 308–309 (2015) [Math. Notes 98, 336–338 (2015)].MathSciNetzbMATHCrossRefGoogle Scholar
  67. 67.
    S. V. Konyagin and A. A. Kuleshov, “On some properties of finite sums of ridge functions defined on convex subsets of Rn,” Tr. Mat. Inst. im. V.A. Steklova, Ross. Akad. Nauk 293, 193–200 (2016) [Proc. Steklov Inst. Math. 293, 186–193 (2016)].zbMATHGoogle Scholar
  68. 68.
    S. V. Konyagin and V. N. Temlyakov, “Some error estimates in learning theory,” in Approximation Theory: A Volume Dedicated to Borislav Bojanov, Ed. by D. K. Dimitrov, G. Nikolov, and R. Uluchev (Marin Drinov Acad. Publ. House, Sofia, 2004), pp. 126–144.Google Scholar
  69. 69.
    A. Kroó, “On approximation by ridge functions,” Constr. Approx. 13 (4), 447–460 (1997).MathSciNetzbMATHCrossRefGoogle Scholar
  70. 70.
    A. A. Kuleshov, “On some properties of smooth sums of ridge functions,” Tr. Mat. Inst. im. V.A. Steklova, Ross. Akad. Nauk 294, 99–104 (2016) [Proc. Steklov Inst. Math. 294, 89–94 (2016)].MathSciNetzbMATHGoogle Scholar
  71. 71.
    A. A. Kuleshov, “Continuous sums of ridge functions on a convex body and the class VMO,” Mat. Zametki 102 (6), 866–873 (2017) [Math. Notes 102, 799–805 (2017)].MathSciNetzbMATHCrossRefGoogle Scholar
  72. 72.
    A. A. Kuleshov, “Continuous sums of ridge functions on a convex body with Dini condition on moduli of continuity at boundary points,” Anal. Math. (in press).Google Scholar
  73. 73.
    V. Kůrková, “Approximation of functions by perceptron networks with bounded number of hidden units,” Neural Networks 8 (5), 745–750 (1995).CrossRefGoogle Scholar
  74. 74.
    V. Kůrková, “Trade-off between the size of parameters and the number of units in one-hidden-layer networks,” Neural Network World 6 (2), 191–200 (1996).Google Scholar
  75. 75.
    W. Light, “Ridge functions, sigmoidal functions and neural networks,” in Approximation Theory VII: Proc. 7th Int. Symp., Austin, TX, 1992, Ed. by E. W. Cheney et al. (Academic, Boston, 1993), pp. 163–206.Google Scholar
  76. 76.
    W. A. Light and H. S. J. Wayne, “Some aspects of radial basis function approximation,” in Approximation Theory, Spline Functions and Applications: Proc. NATO Adv. Study Inst., Maratea, 1991, Ed. by S. P. Singh et al. (Kluwer, Dordrecht, 1992), pp. 163–190.CrossRefGoogle Scholar
  77. 77.
    S. Lin, F. Cao, and Z. Xu, “Essential rate for approximation by spherical neural networks,” Neural Networks 24 (7), 752–758 (2011).zbMATHCrossRefGoogle Scholar
  78. 78.
    V. Ya. Lin and A. Pinkus, “Fundamentality of ridge functions,” J. Approx. Theory 75 (3), 295–311 (1993).MathSciNetzbMATHCrossRefGoogle Scholar
  79. 79.
    V. Ya. Lin and A. Pinkus, “Approximation of multivariate functions,” in Advances in Computational Mathematics: Proc. Conf., New Delhi, 1993, Ed. by H. P. Dikshit and C. A. Micchelli (World Sci., Singapore, 1994), pp. 257–265.Google Scholar
  80. 80.
    B. F. Logan and L. A. Shepp, “Optimal reconstruction of a function from its projections,” Duke Math. J. 42 (4), 645–659 (1975).MathSciNetzbMATHCrossRefGoogle Scholar
  81. 81.
    W. R. Madych and S. A. Nelson, “Multivariate interpolation and conditionally positive definite functions. II,” Math. Comput. 54, 211–230 (1990).MathSciNetzbMATHCrossRefGoogle Scholar
  82. 82.
    V. E. Maiorov, “On best approximation by ridge functions,” J. Approx. Theory 99 (1), 68–94 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  83. 83.
    V. Maiorov, “On best approximation of classes by radial functions,” J. Approx. Theory 120 (1), 36–70 (2003).MathSciNetzbMATHCrossRefGoogle Scholar
  84. 84.
    V. Maiorov, “On lower bounds in radial basis approximation,” Adv. Comput. Math. 22 (2), 103–113 (2005).MathSciNetzbMATHCrossRefGoogle Scholar
  85. 85.
    V. Maiorov, “Optimal non-linear approximation using sets of finite pseudodimension,” East J. Approx. 11 (1), 1–19 (2005).MathSciNetzbMATHGoogle Scholar
  86. 86.
    V. Maiorov, “Pseudo-dimension and entropy of manifolds formed by affine-invariant dictionary,” Adv. Comput. Math. 25 (4), 435–450 (2006).MathSciNetzbMATHCrossRefGoogle Scholar
  87. 87.
    V. Maiorov, “Approximation by neural networks and learning theory,” J. Complexity 22 (1), 102–117 (2006).MathSciNetzbMATHCrossRefGoogle Scholar
  88. 88.
    V. E. Maiorov, “Best approximation by ridge functions in Lp-spaces,” Ukr. Math. J. 62 (3), 452–466 (2010).CrossRefGoogle Scholar
  89. 89.
    V. Maiorov, “Geometric properties of the ridge function manifold,” Adv. Comput. Math. 32 (2), 239–253 (2010).MathSciNetzbMATHCrossRefGoogle Scholar
  90. 90.
    V. E. Maiorov and R. Meir, “On the near optimality of the stochastic approximation of smooth functions by neural networks,” Adv. Comput. Math. 13 (1), 79–103 (2000).MathSciNetzbMATHCrossRefGoogle Scholar
  91. 91.
    V. Maiorov and R. Meir, “Lower bounds for multivariate approximation by affine-invariant dictionaries,” IEEE Trans. Inf. Theory 47 (4), 1569–1575 (2001).MathSciNetzbMATHCrossRefGoogle Scholar
  92. 92.
    V. E. Maiorov, R. Meir, and J. Ratsaby, “On the approximation of functional classes equipped with a uniform measure using ridge functions,” J. Approx. Theory 99 (1), 95–111 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  93. 93.
    V. E. Maiorov, K. I. Oskolkov, and V. N. Temlyakov, “Gridge approximation and Radon compass,” in Approximation Theory: A Volume Dedicated to B. Sendov, Ed. by B. D. Bojanov (DARBA, Sofia, 2002), pp. 284–309.zbMATHGoogle Scholar
  94. 94.
    V. Maiorov and A. Pinkus, “Lower bounds for approximation by MLP neural networks,” Neurocomputing 25, 81–91 (1999).zbMATHCrossRefGoogle Scholar
  95. 95.
    Y. Makovoz, “Random approximants and neural networks,” J. Approx. Theory 85 (1), 98–109 (1996).MathSciNetzbMATHCrossRefGoogle Scholar
  96. 96.
    D. E. Marshall and A. G. O’Farrell, “Uniform approximation by real functions,” Fundam. Math. 104, 203–211 (1979).MathSciNetzbMATHCrossRefGoogle Scholar
  97. 97.
    R. Meir and V. E. Maiorov, “On the optimality of neural-network approximation using incremental algorithms,” IEEE Trans. Neural Netw. 11 (2), 323–337 (2000).CrossRefGoogle Scholar
  98. 98.
    H. N. Mhaskar, “Neural networks for optimal approximation of smooth and analytic functions,” Neural Comput. 8 (1), 164–177 (1996).CrossRefGoogle Scholar
  99. 99.
    H. N. Mhaskar and C. A. Micchelli, “Approximation by superposition of sigmoidal and radial basis functions,” Adv. Appl. Math. 13 (3), 350–373 (1992).MathSciNetzbMATHCrossRefGoogle Scholar
  100. 100.
    H. N. Mhaskar and C. A. Micchelli, “Degree of approximation by neural and translation networks with a single hidden layer,” Adv. Appl. Math. 16 (2), 151–183 (1995).MathSciNetzbMATHCrossRefGoogle Scholar
  101. 101.
    H. N. Mhaskar, F. J. Narcowich, and J. D. Ward, “Approximation properties of zonal function networks using scattered data on the sphere,” Adv. Comput. Math. 11 (2–3), 121–137 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  102. 102.
    F. J. Narcowich, J. D. Ward, and H. Wendland, “Refined error estimates for radial basis function interpolation,” Constr. Approx. 19 (4), 541–564 (2003).MathSciNetzbMATHCrossRefGoogle Scholar
  103. 103.
    Yu. P. Ofman, “Best approximation of functions of two variables by functions of the form φ(x) + ψ(y),” Izv. Akad. Nauk SSSR, Ser. Mat. 25 (2), 239–252 (1961) [Am. Math. Soc. Transl., Ser. 2, 44, 12–28 (1965)].MathSciNetGoogle Scholar
  104. 104.
    A. Olevskii, “Completeness in L2(R) of almost integer translates,” C. R. Acad. Sci. Paris, Sér. 1, 324 (9), 987–991 (1997).MathSciNetzbMATHCrossRefGoogle Scholar
  105. 105.
    K. I. Oskolkov, “Ridge approximation, Chebyshev–Fourier analysis and optimal quadrature formulas,” Tr. Mat. Inst. im. V.A. Steklova, Ross. Akad. Nauk 219, 269–285 (1997) [Proc. Steklov Inst. Math. 219, 265–280 (1997)].zbMATHGoogle Scholar
  106. 106.
    K. I. Oskolkov, “Linear and nonlinear methods of relief approximation,” in Metric Theory of Functions and Related Problems of Analysis (AFTs, Moscow, 1999), pp. 165–195. Engl. transl.: J. Math. Sci. 155 (1), 129–152 (2008).Google Scholar
  107. 107.
    P. P. Petrushev, “Approximation by ridge functions and neural networks,” SIAM J. Math. Anal. 30 (1), 155–189 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  108. 108.
    A. Pinkus, “Some density problems in multivariate approximation,” in Approximation Theory: Proc. IDoMAT 95 (Akad. Verlag, Berlin, 1995), pp. 277–284.Google Scholar
  109. 109.
    A. Pinkus, “TDI-subspaces of C(Rd) and some density problems from neural networks,” J. Approx. Theory 85 (3), 269–287 (1996).MathSciNetzbMATHCrossRefGoogle Scholar
  110. 110.
    A. Pinkus, “Approximating by ridge functions,” in Surface Fitting and Multiresolution Methods (Vanderbilt Univ. Press, Nashville, TN, 1997), pp. 279–292.Google Scholar
  111. 111.
    A. Pinkus, “Approximation theory of the MLP model in neural networks,” Acta Numerica 8, 143–195 (1999).MathSciNetzbMATHCrossRefGoogle Scholar
  112. 112.
    A. Pinkus, Ridge Functions (Cambridge Univ. Press, Cambridge, 2015), Cambridge Tracts Math. 205.zbMATHCrossRefGoogle Scholar
  113. 113.
    G. Pisier, “Remarques sur un résultat non publié de B. Maurey,” in Séminaire d’Analyse Fonctionnelle 1980–1981 (éc. Polytech., Cent. Math., Palaiseau, 1981), Exp.5.zbMATHGoogle Scholar
  114. 114.
    M. K. Potapov, “Approximation ‘by an angle’,” in Proc. Conf. on Constructive Theory of Functions (Approximation Theory), Budapest, 1969 (Akad. Kiadó, Budapest, 1972), pp. 371–399.Google Scholar
  115. 115.
    M. K. Potapov, “Approximation ‘by an angle’ and embedding theorems,” Math. Balk. 2, 183–198 (1972).Google Scholar
  116. 116.
    M. K. Potapov, “The Hardy–Littlewood and Marcinkiewicz–Littlewood–Paley theorems, approximation ‘by an angle’, and the imbedding of certain classes of functions,” Mathematica 14 (2), 339–362 (1972).MathSciNetGoogle Scholar
  117. 117.
    M. K. Potapov, “Imbedding classes of functions with dominant mixed modulus of smoothness,” Tr. Mat. Inst. im. V.A. Steklova, Akad. Nauk SSSR 131, 199–210 (1974) [Proc. Steklov Inst. Math. 131, 206–218 (1975)].Google Scholar
  118. 118.
    M. K. Potapov, “Imbedding theorems in a mixed metric,” Tr. Mat. Inst. im. V.A. Steklova, Akad. Nauk SSSR 156, 143–156 (1980) [Proc. Steklov Inst. Math. 156, 155–171 (1983)].MathSciNetzbMATHGoogle Scholar
  119. 119.
    M. K. Potapov, B. V. Simonov, and S. Yu. Tikhonov, “Mixed moduli of smoothness in Lp, 1 < p < 8: a survey,” Surv. Approx. Theory 8, 1–57 (2013).MathSciNetzbMATHGoogle Scholar
  120. 120.
    M. J. D. Powell, “The theory of radial basis function approximation in 1990,” in Advances in Numerical Analysis, Vol. 2: Wavelets, Subdivision Algorithms, and Radial Basis Functions, Ed. by W. Light (Clarendon, Oxford, 1992), pp. 105–210.Google Scholar
  121. 121.
    J. Ratsaby and V. Maiorov, “On the value of partial information for learning from examples,” J. Complexity 13 (4), 509–544 (1997).MathSciNetzbMATHCrossRefGoogle Scholar
  122. 122.
    R. Schaback, “Approximation by radial basis functions with finitely many centers,” Constr. Approx. 12 (3), 331–340 (1996).MathSciNetzbMATHCrossRefGoogle Scholar
  123. 123.
    L. Schwartz, “Sur certaines familles non fondamentales de fonctions continues,” Bull. Soc. Math. France 72, 141–145 (1944).MathSciNetzbMATHCrossRefGoogle Scholar
  124. 124.
    E. M. Stein and G. Weiss, Introduction to Fourier Analysis on Euclidean Spaces (Princeton Univ. Press, Princeton, NJ, 1971).zbMATHGoogle Scholar
  125. 125.
    M. I. Stesin, “Aleksandrov diameters of finite-dimensional sets and classes of smooth functions,” Dokl. Akad. Nauk SSSR 220 (6), 1278–1281 (1975) [Sov. Math., Dokl. 16, 252–256 (1975)].MathSciNetzbMATHGoogle Scholar
  126. 126.
    V. N. Temlyakov, Approximation of Periodic Functions (Nova Sci. Publ., Commack, NY, 1993).zbMATHGoogle Scholar
  127. 127.
    V. N. Temlyakov, “On approximation by ridge functions,” Preprint (Dept. Math., Univ. S. Carol., Columbia, SC, 1996).Google Scholar
  128. 128.
    V. N. Temlyakov, “Nonlinear methods of approximation,” Found. Comput. Math. 3 (1), 33–107 (2003).MathSciNetzbMATHCrossRefGoogle Scholar
  129. 129.
    V. Temlyakov, Greedy Approximation (Cambridge Univ. Press, Cambridge, 2011).zbMATHCrossRefGoogle Scholar
  130. 130.
    V. M. Tikhomirov, Some Problems in Approximation Theory (Mosk. Gos. Univ., Moscow, 1976) [in Russian].Google Scholar
  131. 131.
    S. B. Vakarchuk, “K-functionals and n-widths of classes of periodic functions of two variables,” East J. Approx. 8 (2), 161–182 (2002).MathSciNetzbMATHGoogle Scholar
  132. 132.
    S. B. Vakarchuk and A. V. Shvachko, “Kolmogorov-type inequalities for derived functions of two variables with application for approximation by an ‘angle’,” Izv. Vyssh. Uchebn. Zaved., Mat., No. 11, 3–22 (2015) [Russ. Math. 59 (11), 1–18 (2015)].MathSciNetzbMATHGoogle Scholar
  133. 133.
    F. P. Vasil’ev, Optimization Methods (Faktorial, Moscow, 2002) [in Russian].Google Scholar
  134. 134.
    N. Ya. Vilenkin, Special Functions and the Theory of Group Representations (Nauka, Moscow, 1965; Am. Math. Soc., Providence, RI, 1968).zbMATHCrossRefGoogle Scholar
  135. 135.
    A. G. Vitushkin, “Some properties of linear superpositions of smooth functions,” Dokl. Akad. Nauk SSSR 156 (5), 1003–1006 (1964) [Sov. Math., Dokl. 5, 741–744 (1964)].MathSciNetzbMATHGoogle Scholar
  136. 136.
    A. G. Vitushkin, “Proof of the existence of analytic functions of several complex variables which are not representable by superpositions of continuously differentiable functions of fewer variables,” Dokl. Akad. Nauk SSSR 156 (6), 1258–1261 (1964) [Sov. Math., Dokl. 5, 793–796 (1964)].MathSciNetzbMATHGoogle Scholar
  137. 137.
    A. G. Vitushkin, “On Hilbert’s thirteenth problem,” in Hilbert’s Problems, Ed. by P. S. Aleksandrov (Nauka, Moscow, 1969), pp. 163–170 [in Russian].Google Scholar
  138. 138.
    B. A. Vostretsov and M. A. Kreines, “Approximation of continuous functions by superpositions of plane waves,” Dokl. Akad. Nauk SSSR 140 (6), 1237–1240 (1961) [Sov. Math., Dokl. 2, 1326–1329 (1961)].MathSciNetGoogle Scholar
  139. 139.
    H. Wendland, “Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree,” Adv. Comput. Math. 4, 389–396 (1995).MathSciNetzbMATHCrossRefGoogle Scholar
  140. 140.
    H. Wendland, “Error estimates for interpolation by compactly supported radial basis functions of minimal degree,” J. Approx. Theory 93 (2), 258–272 (1998).MathSciNetzbMATHCrossRefGoogle Scholar
  141. 141.
    Z.-M. Wu and R. Schaback, “Local error estimates for radial basis function interpolation of scattered data,” IMA J. Numer. Anal. 13 (1), 13–27 (1993).MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Pleiades Publishing, Ltd. 2018

Authors and Affiliations

  • S. V. Konyagin
    • 1
  • A. A. Kuleshov
    • 2
  • V. E. Maiorov
    • 3
  1. 1.Steklov Mathematical Institute of Russian Academy of SciencesMoscowRussia
  2. 2.Laboratory “Multidimensional Approximation and Applications,”Moscow State UniversityMoscowRussia
  3. 3.Technion – Israel Institute of TechnologyHaifaIsrael

Personalised recommendations