Advertisement

Convexity and Intersection of Random Spaces

  • Mariya Shcherbina
  • Brunello Tirozzi
Part of the Developments in Mathematics book series (DEVM, volume 8)

Abstract

The problem of finding the volume of the intersection of the N dimensional sphere with p = αN random half spaces when α is less than a critical value α c , and when N,p → ∞is solved rigorously. The asymptotic expression coincides with the one found by E. Gardner ([4]), using non rigorous replica calculations in neural network theory. When α is larger than α c the volume of the intersection goes to 0 more rapidly than exp(— N const). We use the cavity method. The convexity of the volume and the Brunn Minkowski theorem ([3]) have a central role in the proof.

Keywords

Random systems Convexity 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Bovier A., Gayrard V., Hopfield Models as a Generalized Random Mean Field Models, Mathematical Aspects of Spin Glasses and Neuronal Networks, A. Bovier, P. Picco Eds., Progress in Probability, Birkhauser, 41 (1998), 3–89.Google Scholar
  2. [2]
    Brascamp H.J., Lieb E.H., On the Extension of the Brunn-Minkowsky and Pekoda-Leindler Theorems, Includings Inequalities for Log Concave functions, and with an application to the diffusion equation. J. Func. Anal. 22 (1976) 366–389.MathSciNetzbMATHCrossRefGoogle Scholar
  3. [3]
    Hadwiger H., Vorlesungen uber Inhalt, Oberlache und Isoperimetrie. Springer-Verlag, 1957.Google Scholar
  4. [4]
    Gardner G., The Space of Interactions in Neural Network Models, J.Phys.A: Math.Gen. 21 (1988) 271–284.CrossRefGoogle Scholar
  5. [5]
    Gardner E., Derrida B., Optimal Stage Properties of Neural Network Models, J.Phys.A: Math.Gen. 21 (1988) 257–270.MathSciNetCrossRefGoogle Scholar
  6. [6]
    Ghirlanda S., Guerra F., General Properties of Overlap Probability Distributions in Disordered Spin System, J.Phys.A: Math.Gen. 31(1988)9149–9155.Google Scholar
  7. [7]
    Mezard, M., Parisi, G., Virasoro, M.A., Spin Glass Theory and Beyond, Singapore, World Scientific, 1987.zbMATHGoogle Scholar
  8. [8]
    Pastur L., Shcherbina M., Absence of Self-Averaging of the Order Parameter in the Sherrington-Kirkpatrick Model. J.Stat.Phys. 62 (1991) 1–26.MathSciNetCrossRefGoogle Scholar
  9. [9]
    Pastur L., Shcherbina M., Tirozzi B., The Replica-Symmetric Solution Without Replica Trick for the Hopfield Model. J. Stat. Phys. 74 5 /6 (1994) 1161–1183.MathSciNetCrossRefGoogle Scholar
  10. [10]
    Pastur L., Shcherbina M., Tirozzi B., On the Replica Symmetric Equations for the Hopfield Model, J.Math.Phys. 40 8 (1999) 3930–3947.MathSciNetzbMATHCrossRefGoogle Scholar
  11. [11]
    Shcherbina M., On the Replica Symmetric Solution for the Sherrington-Kirkpatrick Model, Helvetica Physica Acta 70 (1997) 772–797.MathSciNetGoogle Scholar
  12. [12]
    Shcherbina M., Some Estimates for the Critical Temperature of The Sherrington-Kirkpatrick Model with Magnetic Field, Mathematical Results in Statistical Mechanics World Scientific, Singapore (1999) 455–474.Google Scholar
  13. [13]
    Shcherbina M., Tirozzi, B., Rigorous Solution of the Gardner Problem, to appear.Google Scholar
  14. [14]
    Talagrand M., Rigorous Results for the Hopfield Model with Many Patterns. Prob. Theor. Rel. Fields 110 (1998) 176–277.Google Scholar
  15. [15]
    Talagrand M., Exponential Inequalities and Replica Symmetry Breaking for the Sherrington-Kirkpatrick Model, Ann.Probab. 28 (2000) 1018–1068.MathSciNetzbMATHCrossRefGoogle Scholar
  16. [16]
    Talagrand M., Intersecting Random Half-Spaces: Toward the Gardner-Derrida Problem, Ann.Probab. 28 (2000) 725–758.MathSciNetzbMATHCrossRefGoogle Scholar
  17. [17]
    Talagrand M., Self Averaging and the Space of Interactions in Neural Networks, Random Structures and Algorithms 14 (1988) 199–213.MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2002

Authors and Affiliations

  • Mariya Shcherbina
    • 1
  • Brunello Tirozzi
    • 2
  1. 1.Institute for Low TemperaturesUkr. Ak. SciKharkovUkraine
  2. 2.Department of PhysicsUniversity of Rome “La Sapienza”RomaItaly

Personalised recommendations