Computing the number of metastable states in infinite-range models
Giorgio Parisi

TL;DR
This paper reviews recent results on calculating the large number of metastable states in infinite-range disordered models, highlighting the role of supersymmetry and its breaking, especially in the context of spin glasses.
Contribution
It provides a detailed analysis of the computation of metastable states in infinite-range models and elucidates the significance of supersymmetry in this context.
Findings
Most stationary points in the Sherrington-Kirkpatrick model are saddles.
Supersymmetry is crucial in understanding the landscape of stationary points.
Supersymmetry breaking has significant physical implications.
Abstract
In these notes I will review the results that have been obtained in these last years on the computation of the number of metastable states in infinite-range models of disordered systems. This is a particular case of the problem of computing the exponentially large number of stationary points of a random function. Quite surprisingly supersymmetry plays a crucial role in this problem. A careful analysis of the physical implication of supersymmetry and of supersymmetry breaking will be presented: the most spectacular one is that in the Sherrington-Kirkpatrick model for spin glasses most of the stationary points are saddles, as predicted long time ago.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNeural Networks and Applications
