Spin glass theory and its new challenge: structured disorder
Author:
Open Access
- 10 December 2023
- journal article
- research article
- Published by Springer Nature in Indian Journal of Physics
- Vol. 98 (11) , 3757-3768
Abstract
This paper first describes, from a high-level viewpoint, the main challenges that had to be solved in order to develop a theory of spin glasses in the last fifty years. It then explains how important inference problems, notably those occurring in machine learning, can be formulated as problems in statistical physics of disordered systems. However, the main questions that we face in the analysis of deep networks require to develop a new chapter of spin glass theory, which will address the challenge of structured data.Keywords
All Related Versions
Funding Information
- eu (PE1 FAIR - Future Artificial Intelligence Research (CUP B43C22000800006))
- Università Commerciale Luigi Bocconi
This publication has 39 references indexed in Scilit:
- Entropy landscape of solutions in the binary perceptron problemJournal of Physics A: Mathematical and Theoretical, 2013
- The Nature of Statistical Learning TheoryTechnometrics, 1996
- Analytical solution of the off-equilibrium dynamics of a long-range spin-glass modelPhysical Review Letters, 1993
- The sphericalp-spin interaction spin glass model: the staticsZeitschrift für Physik B Condensed Matter, 1992
- Statistical mechanics of learning from examplesPhysical Review A, 1992
- First-order transition to perfect generalization in a neural network with binary synapsesPhysical Review A, 1990
- The space of interactions in neural networks: Gardner's computation with the cavity methodJournal of Physics A: General Physics, 1989
- Three unfinished works on the optimal storage capacity of networksJournal of Physics A: General Physics, 1989
- SK Model: The Replica Solution without ReplicasEurophysics Letters, 1986
- Solution of 'Solvable model of a spin glass'Philosophical Magazine, 1977