Fetching the paper…
Reading the bibliography…
We study the approximation properties of shallow neural networks with an activation function which is a power of the rectified linear unit.
The Aeronautical Journal 72
Argyris, J.H., Fried, I., Scharpf, D.W.: The tuba family of plate elements for the matrix displacement method · 1968
Earlier work this paper cites.
Mathematics of Computation 24
Bramble, J.H., Zlámal, M.: Triangular elements in the finite element method · 1970
Earlier work this paper cites.
28. Princeton university press (1970)
Rockafellar, R.T.: Convex analysis · 1970
Earlier work this paper cites.
Numerische Mathematik 15
Ženíšek, A.: Interpolation polynomials on the triangle · 1970
Earlier work this paper cites.
Berge, C.: Graphs and hypergraphs (1973)
1973
Earlier work this paper cites.
Séminaire Analyse fonctionnelle (dit “Maurey-Schwartz") pp. 1–12 (1981)
Pisier, G.: Remarques sur un résultat non publié de b. maurey · 1981
Earlier work this paper cites.
Longman scientific & technical Harlow (1989)
Erdös, P., Gruber, P.M., Hammer, J.: Lattice points · 1989
Earlier work this paper cites.
Neural networks 4
Hornik, K.: Approximation capabilities of multilayer feedforward networks · 1991
Earlier work this paper cites.
SIAM (1992)
Daubechies, I.: Ten lectures on wavelets · 1992
Earlier work this paper cites.
The annals of Statistics 20
Jones, L.K.: A simple lemma on greedy approximation in hilbert space and convergence rates for projection pursuit regression and neural network training · 1992
Earlier work this paper cites.
IEEE Transactions on Information theory 39
Barron, A.R.: Universal approximation bounds for superpositions of a sigmoidal function · 1993
Earlier work this paper cites.
Springer Science & Business Media (1993)
DeVore, R.A., Lorentz, G.G.: Constructive approximation, vol. 303 · 1993
Earlier work this paper cites.
Neural networks 6
Hornik, K.: Some new results on neural network approximation · 1993
Earlier work this paper cites.
Applied mathematics letters 6
Kainen, P.C., Kurková, V.: Quasiorthogonal dimension of euclidean spaces · 1993
Earlier work this paper cites.
Neural networks 6
Leshno, M., Lin, V.Y., Pinkus, A., Schocken, S.: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function · 1993
Earlier work this paper cites.
In: Proceedings of 27th Asilomar conference on signals, systems and computers, pp. 40–44. IEEE (1993)
Pati, Y.C., Rezaiifar, R., Krishnaprasad, P.S.: Orthogonal matching pursuit: Recursive function approximation with applications to wavelet decomposition · 1993
Earlier work this paper cites.
Acta Numerica 3
Ellacott, S.: Aspects of the numerical analysis of neural networks · 1994
Earlier work this paper cites.
Neural Computation 6
Hornik, K., Stinchcombe, M., White, H., Auer, P.: Degree of approximation results for feedforward networks approximating unknown mappings and their derivatives · 1994
Earlier work this paper cites.
Unpublished manuscript (1995)
Donoho, D., Johnstone, I.: Empirical atomic decomposition · 1995
Earlier work this paper cites.
Springer (1996)
Lorentz, G.G., Golitschek, M.v., Makovoz, Y.: Constructive approximation: advanced problems, vol. 304 · 1996
Cited alongside, same era.
Journal of Approximation Theory 85
Makovoz, Y.: Random approximants and neural networks · 1996
Cited alongside, same era.
Neural networks 10
Attali, J.G., Pagès, G.: Approximations of functions by a multilayer perceptron: a new approach · 1997
Cited alongside, same era.
Stanford University (1998)
Candes, E.J.: Ridgelets: theory and applications · 1998
Cited alongside, same era.
Acta numerica 7
DeVore, R.A.: Nonlinear approximation · 1998
Cited alongside, same era.
SIAM Journal on Mathematical Analysis 30
Petrushev, P.P.: Approximation by ridge functions and neural networks · 1998
Cited alongside, same era.
Journal of Approximation Theory 99
Mathematics of Computation 83
Lin, Q., Xie, H., Xu, J.: Lower bounds of the discretization error for piecewise polynomials · 2014
Later among the works it cites.
Annali di Matematica Pura ed Applicata (1923-) 194
Costarelli, D., Spigler, R.: Approximation by series of sigmoidal functions with applications to neural networks · 2015
Later among the works it cites.
Manuscript. Available at http://math. mit. edu/˜ stevenj/bump-saddle. pdf (2015)
Johnson, S.G.: Saddle-point integration of C ∞ bump functions · 2015
Later among the works it cites.
The Journal of Machine Learning Research 18
Bach, F.: Breaking the curse of dimensionality with convex neural networks · 2017
Later among the works it cites.
Neural Networks 94
Yarotsky, D.: Error bounds for approximations with deep relu networks · 2017
Later among the works it cites.
IEEE Transactions on Information Theory 64
Klusowski, J.M., Barron, A.R.: Approximation by combinations of relu and squared relu ridge functions with ℓ 1 \ell^{1} and ℓ 0 \ell^{0} controls · 2018
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Maiorov, V.: On best approximation by ridge functions · 1999
Cited alongside, same era.
Constructive approximation 18
Gordon, Y., Maiorov, V., Meyer, M., Reisner, S.: On the best approximation by ridge functions in the uniform norm · 2001
Cited alongside, same era.
IEEE Transactions on Information Theory 47
Kurková, V., Sanguineti, M.: Bounds on rates of variable-basis and neural-network approximation · 2001
Cited alongside, same era.
IEEE Transactions on Neural Networks 13
Lavretsky, E.: On the geometric convergence of neural approximations · 2002
Cited alongside, same era.
Acta numerica 13
Bungartz, H.J., Griebel, M.: Sparse grids · 2004
Cited alongside, same era.
Advances in neural information processing systems 18
Bengio, Y., Delalleau, O., Le Roux, N.: The curse of highly variable functions for local kernel machines · 2006
Cited alongside, same era.
Later among the works it cites.
arXiv preprint arXiv:1802.03620 (2018)
Yarotsky, D.: Optimal approximation of continuous functions by very deep relu networks · 2018
Later among the works it cites.
arXiv preprint arXiv:1905.02199 (2019)
Daubechies, I., DeVore, R., Foucart, S., Hanin, B., Petrova, G.: Nonlinear approximation and (deep) relu networks · 2019
Later among the works it cites.
arXiv preprint arXiv:1906.08039 (2019)
E, W., Ma, C., Wu, L.: Barron spaces and the compositional function spaces for neural network models · 2019
Later among the works it cites.
arXiv preprint arXiv:1903.05858 (2019)
Li, B., Tang, S., Yu, H.: Better approximations of high dimensional smooth functions by deep neural networks with rectified power units · 2019
Later among the works it cites.
arXiv preprint arXiv:2006.04048 (2020)
Bresler, G., Nagaraj, D.: Sharp representation theorems for relu networks with precise dependence on depth · 2020
Closest in time.
Neural Networks 128
Siegel, J.W., Xu, J.: Approximation rates for neural networks with general activation functions · 2020
Closest in time.
Communications in Computational Physics 28
Xu, J.: Finite neuron method and convergence analysis · 2020
Closest in time.
Advances in Neural Information Processing Systems 33
Yarotsky, D., Zhevnerchuk, A.: The phase diagram of approximation rates for deep neural networks · 2020
Closest in time.
arXiv preprint arXiv:2101.01708 (2021)
Lu, J., Lu, Y., Wang, M.: A priori generalization analysis of the deep ritz method for solving high dimensional elliptic equations · 2021
Closest in time.
arXiv preprint arXiv:2106.15002 (2021)
Siegel, J.W., Xu, J.: Characterization of the variation spaces corresponding to shallow neural networks · 2021
Closest in time.
arXiv preprint arXiv:2106.15000 (2021)
Siegel, J.W., Xu, J.: Improved convergence rates for the orthogonal greedy algorithm · 2021
Closest in time.
arXiv preprint arXiv:2101.12365 (2021)
Siegel, J.W., Xu, J.: Sharp bounds on the approximation rates, metric entropy, and n n -widths of shallow neural networks · 2021
Closest in time.