Complexity of random smooth functions on the high-dimensional sphere

TL;DR

This paper investigates the complexity of smooth Gaussian functions on high-dimensional spheres, providing explicit formulas for critical points and level sets, revealing two possible landscape scenarios with implications for spin glass models.

Contribution

It introduces explicit asymptotic formulas for the number of critical points and Euler characteristics of Gaussian functions on high-dimensional spheres, highlighting two distinct landscape scenarios.

Findings

Two landscape scenarios with different critical point structures

Explicit asymptotic formulas for critical points and level sets

Implications for understanding spin glass models

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.