The Annals of Probability

Complexity of random smooth functions on the high-dimensional sphere

Antonio Auffinger and Gerard Ben Arous

Full-text: Open access

Abstract

We analyze the landscape of general smooth Gaussian functions on the sphere in dimension $N$, when $N$ is large. We give an explicit formula for the asymptotic complexity of the mean number of critical points of finite and diverging index at any level of energy and for the mean Euler characteristic of level sets. We then find two possible scenarios for the bottom landscape, one that has a layered structure of critical values and a strong correlation between indexes and critical values and another where even at levels below the limiting ground state energy the mean number of local minima is exponentially large. We end the paper by discussing how these results can be interpreted in the language of spin glasses models.

Article information

Source
Ann. Probab., Volume 41, Number 6 (2013), 4214-4247.

Dates
First available in Project Euclid: 20 November 2013

Permanent link to this document
https://projecteuclid.org/euclid.aop/1384957786

Digital Object Identifier
doi:10.1214/13-AOP862

Mathematical Reviews number (MathSciNet)
MR3161473

Zentralblatt MATH identifier
1288.15045

Subjects
Primary: 15A52 82D30: Random media, disordered materials (including liquid crystals and spin glasses) 60G60: Random fields

Keywords
Sample spin glasses critical points random matrices Parisi formula

Citation

Auffinger, Antonio; Ben Arous, Gerard. Complexity of random smooth functions on the high-dimensional sphere. Ann. Probab. 41 (2013), no. 6, 4214--4247. doi:10.1214/13-AOP862. https://projecteuclid.org/euclid.aop/1384957786


Export citation

References

  • [1] Adler, R. J. and Taylor, J. E. (2007). Random Fields and Geometry. Springer, New York.
  • [2] Auffinger, A., Ben Arous, G. and Černý, J. (2013). Random matrices and complexity of spin glasses. Comm. Pure Appl. Math. 66 165–201.
  • [3] Azaïs, J.-M. and Wschebor, M. (2009). Level Sets and Extrema of Random Processes and Fields. Wiley, Hoboken, NJ.
  • [4] Ben Arous, G. and Guionnet, A. (1997). Large deviations for Wigner’s law and Voiculescu’s non-commutative entropy. Probab. Theory Related Fields 108 517–542.
  • [5] Bleistein, N. and Handelsman, R. A. (2010). Asymptotic Expansions of Integrals, 2nd ed. Dover, New York.
  • [6] Crisanti, A. and Leuzzi, L. (2004). Spherical $2+p$ spin-glass model: An exactly solvable model for glass to spin-glass transition. Phys. Rev. Lett. 93 21203–21207.
  • [7] Crisanti, A. and Sommers, H. J. (1995). On the tap approach to the spherical $p$-spin sg model. J. Phys. I France 5 805–813.
  • [8] Dembo, A. and Zeitouni, O. (1998). Large Deviations Techniques and Applications, 2nd ed. Applications of Mathematics (New York) 38. Springer, New York.
  • [9] Fyodorov, Y. V. (2004). Complexity of random energy landscapes, glass transition, and absolute value of the spectral determinant of random matrices. Phys. Rev. Lett. 92 240601, 4.
  • [10] Fyodorov, Y. V. and Williams, I. (2007). Replica symmetry breaking condition exposed by random matrix calculation of landscape complexity. J. Stat. Phys. 129 1081–1116.
  • [11] Plancherel, M. and Rotach, W. (1929). Sur les valeurs asymptotiques des polynomes d’Hermite $H_{n}(x)=(-I)^{n}e^{{{x^{2}}}/{2}}\frac{{d^{n}}}{{dx^{n}}}({e^{-\frac{{x^{2}}}{2}}})$. Comment. Math. Helv. 1 227–254.
  • [12] Schoenberg, I. J. (1942). Positive definite functions on spheres. Duke Math. J. 9 96–108.
  • [13] Talagrand, M. (2006). The Parisi formula. Ann. of Math. (2) 163 221–263.
  • [14] Taylor, J., Takemura, A. and Adler, R. J. (2005). Validity of the expected Euler characteristic heuristic. Ann. Probab. 33 1362–1396.
  • [15] Taylor, J. E. and Adler, R. J. (2003). Euler characteristics for Gaussian fields on manifolds. Ann. Probab. 31 533–563.
  • [16] Warner, F. W. (1971). Foundations of Differentiable Manifolds and Lie Groups. Scott, Foresman, Glenview.