Learning Functions of Few Arbitrary Linear Parameters in High Dimensions

Foundations of Computational Mathematics

Volumn 12, Issue 2, 2012, Pages 229-262

  Fornasier, Massimo ^a   Schnass, Karin ^b   Vybiral, Jan ^b  

^a TECHNICAL UNIVERSITY OF MUNICH   (Germany)

^b JOHANN RADON INSTITUTE FOR COMPUTATIONAL AND APPLIED MATHEMATICS   (Austria)

Author keywords

Chernoff bounds for sums of positive semidefinite matrices; Compressed sensing; High dimensional function approximation; Stability bounds for invariant subspaces of singular value decompositions

Indexed keywords

EID: 84858753339     PISSN: 16153375     EISSN: 16153383     Source Type: Journal    
DOI: 10.1007/s10208-012-9115-y     Document Type: Article

References (36)

1. R. Ahlswede, A. Winter, Strong converse for identification via quantum channels, IEEE Trans. Inf. Theory48(3), 569-579 (2002).
2. E. Arias-Castro, Y. C. Eldar, Noise folding in compressed sensing, IEEE Signal Process. Lett. 18(8), 478-481 (2011).
3. R. G. Baraniuk, M. Davenport, R. A. DeVore, M. Wakin, A simple proof of the restricted isometry property for random matrices, Constr. Approx. 28(3), 253-263 (2008).
4. H. Bauschke, H. Borwein, On projection algorithms for solving convex feasibility problems, SIAM Rev. 38(3), 367-426 (1996).
5. E. J. Candès, Harmonic analysis of neural networks, Appl. Comput. Harmon. Anal. 6(2), 197-218 (1999).
6. E. J. Candès, Ridgelets: estimating with ridge functions, Ann. Stat. 31(5), 1561-1599 (2003).
7. E. J. Candès, D. L. Donoho, Ridgelets: a key to higher-dimensional intermittency? Philos. Trans. R. Soc., Math. Phys. Eng. Sci. 357(1760), 2495-2509 (1999).
8. E. J. Candès, J. Romberg, T. Tao, Stable signal recovery from incomplete and inaccurate measurements, Commun. Pure Appl. Math. 59(8), 1207-1223 (2006).
9. E. J. Candès, T. Tao, The Dantzig selector: statistical estimation when p is much larger than n, Ann. Stat. 35(6), 2313-2351 (2007).
10. A. Cohen, W. Dahmen, R. A. DeVore, Compressed sensing and best k-term approximation, J. Am. Math. Soc. 22(1), 211-231 (2009).
11. A. Cohen, I. Daubechies, R. A. DeVore, G. Kerkyacharian, D. Picard, Capturing ridge functions in high dimensions from point queries, Constr. Approx. 35(2), 225-243 (2012).
12. R. Courant, D. Hilbert, Methods of Mathematical Physics, II (Interscience, New York, 1962).
13. 1-minimization decoder, Appl. Comput. Harmon. Anal. 27(3), 275-288 (2009).
14. D. L. Donoho, Compressed sensing, IEEE Trans. Inf. Theory52(4), 1289-1306 (2006).
15. M. Fazel, Matrix rank minimization with applications, Ph. D. thesis, Stanford University, Palo Alto, CA, 2002.
16. M. Fornasier, Numerical methods for sparse recovery, in Theoretical Foundations and Numerical Methods for Sparse Recovery, ed. by M. Fornasier, Radon Series on Computational and Applied Mathematics (De Gruyter, Berlin, 2010).
17. M. Fornasier, H. Rauhut, Compressive sensing, in Handbook of Mathematical Methods in Imaging, vol. 1, ed. by O. Scherzer (Springer, Berlin, 2010), pp. 187-229.
18. 1-minimization, Appl. Comput. Harmon. Anal. 29(1), 97-103 (2010).
19. G. Golub, C. F. van Loan, Matrix Computations, 3rd edn. (Johns Hopkins University Press, Baltimore, 1996).
20. F. John, Plane Waves and Spherical Means Applied to Partial Differential Equations (Interscience, New York, 1955).
21. M. Ledoux, The Concentration of Measure Phenomenon (American Mathematical Society, Providence, 2001).
22. B. F. Logan, L. A. Shepp, Optimal reconstruction of a function from its projections, Duke Math. J. 42(4), 645-659 (1975).
23. E. Novak, H. Woźniakowski, Tractability of Multivariate Problems, Volume I: Linear Information, EMS Tracts in Mathematics, vol. 6 (Eur. Math. Soc., Zürich, 2008).
24. E. Novak, H. Woźniakowski, Approximation of infinitely differentiable multivariate functions is intractable, J. Complex. 25, 398-404 (2009).
25. R. I. Oliveira, Sums of random Hermitian matrices and an inequality by Rudelson, Electron. Commun. Probab. 15, 203-212 (2010).
26. S. Oymak, K. Mohan, M. Fazel, B. Hassibi, A simplified approach to recovery conditions for low-rank matrices, in Proc. Intl. Symp. Information Theory (ISIT) (2011).
27. A. Pinkus, Approximation theory of the MLP model in neural networks, Acta Numer. 8, 143-195 (1999).
28. B. Recht, M. Fazel, P. Parillo, Guaranteed minimum rank solutions to linear matrix equations via nuclear norm minimization, SIAM Rev. 52(3), 471-501 (2010).
29. M. Rudelson, R. Vershynin, Sampling from large matrices: an approach through geometric functional analysis, J. ACM54(4), 21 (2007) 19 pp.
30. n (Springer, New York, 1980).
31. K. Schnass, J. Vybíral, Compressed learning of high-dimensional sparse functions, in Proc. ICASSP11 (2011).
32. G. W. Stewart, Perturbation theory for the singular value decomposition, in SVD and Signal Processing, II, ed. by R. J. Vacarro (Amsterdam, Elsevier, 1991).
33. J. A. Tropp, User-friendly tail bounds for sums of random matrices, Found. Comput. Math. (2011). doi: 10. 1007/s10208-011-9099-z.
34. P.-A. Wedin, Perturbation bounds in connection with singular value decomposition, BIT12, 99-111 (1972).
35. H. Weyl, Das asymptotische Verteilungsgesetz der Eigenwerte linearer partieller Differentialgleichungen (mit einer Anwendung auf die Theorie der Hohlraumstrahlung), Math. Ann. 71, 441-479 (1912).
36. 1 minimisation with noisy data, Preprint (2011).