Learning ridge functions with randomized sampling in high dimensions

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2012, Pages 2025-2028

  Tyagi, Hemant ^a   Cevher, Volkan ^a  

^a EPFL   (Switzerland)

Author keywords

high dimensional function approximation; low rank recovery; Ridge functions

Indexed keywords

DIFFERENTIABLE FUNCTIONS; HIGH DIMENSIONS; HIGH-DIMENSIONAL; LOW RANK; LOW-RANK MATRICES; NEIGHBOURHOOD; RANDOM SAMPLE; RANDOMIZED SAMPLING; UNIFORM APPROXIMATION;

ELECTRICAL ENGINEERING;

SIGNAL PROCESSING;

EID: 84867596151     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288306     Document Type: Conference Paper

References (14)

1. A. Cohen, I. Daubechies, R. A. DeVore, G. Kerkyacharian, and D. Picard, "Capturing ridge functions in high dimensions from point queries," Constructive Approximation, pp. 1-19, 2011.
2. B.F. Logan and L.A. Shepp, "Optimal reconstruction of a function from its projections.," Duke Math. J., vol. 42, pp. 645-659, 1975.
3. J.H. Friedman and W. Stuetzel, "Projection pursuit regression.," J. Amer. Statist. Assoc., vol. 76, pp. 817-823, 1981.
4. D.L. Donoho and I.M. Johnstone, "Projection based regression and a duality with kernel methods.," Ann. Statist., vol. 17, pp. 58-106, 1989.
5. P.J. Huber, "Projection pursuit.," Ann. Statist., vol. 13, pp. 435-475, 1985.
6. A. Pinkus, "Approximation theory of the MLP model in neural networks.," Acta Numerica, vol. 8, pp. 143-195, 1999.
7. E.J. Candès, "Harmonic analysis of neural networks.," Appl. Comput. Harmon. Anal., vol. 6, no. 2, pp. 197-218, 1999.
8. E.J. Candès and D.L. Donoho, "Ridgelets: a key to higher dimensional intermittency?," Philos. Trans. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci., vol. 357, no. 1760, pp. 2495-2509, 1999.
9. E.J. Candès, "Ridgelets: Estimating with ridge functions.," Ann. Stat., vol. 31, no. 5, pp. 1561-1599, 2003.
10. M. Fornasier, K. Schnass, and J. Vybíral, "Learning functions of few arbitrary linear parameters in high dimensions," CoRR, vol. abs/1008.3043, 2010.
11. E.J. Candès and Y. Plan, "Tight oracle bounds for low-rank matrix recovery from a minimal number of random measurements," CoRR, vol. abs/1001.0339, 2010.
12. B. Recht, M. Fazel, and P.A. Parrilo, "Guaranteed minimumrank solutions of linear matrix equations via nuclear norm minimization," Submitted to SIAM review, 2007.
13. B. Laurent and P. Massart, "Adaptive estimation of a quadratic functional by model selection," The Annals of Statistics, vol. 28, no. 5, pp. 1302-1338.
14. H. Weyl, "Das asymptotische verteilungsgesetz der eigenwerte linearer partieller differentialgleichungen (mit einer anwendung auf die theorie der hohlraumstrahlung)," Mathematische Annalen, vol. 71, pp. 441-479, 1912.