Arrangement of nearby minima and saddles in the mixed spherical energy landscapes

Abstract

The mixed spherical models were recently found to violate long-held assumptions about mean-field glassy dynamics. In particular, the threshold energy, where most stationary points are marginal and that in the simpler pure models attracts long-time dynamics, seems to lose significance. Here, we compute the typical distribution of stationary points relative to each other in mixed models with a replica symmetric complexity. We examine the stability of nearby points, accounting for the presence of an isolated eigenvalue in their spectrum due to their proximity. Despite finding rich structure not present in the pure models, we find nothing that distinguishes the points that do attract the dynamics. Instead, we find new geometric significance of the old threshold energy, and invalidate pictures of the arrangement of most marginal inherent states into a continuous manifold.

arXiv commentSubmission to SciPost

References in corpus (23)

• Spin-Glass Theory for Pedestrians
• Recipes for metastable states in Spin Glasses
• Phase space geometry and slow dynamics
• On the stationary points of the TAP free energy
• A Landscape Analysis of Constraint Satisfaction Problems
• Unreasonable Effectiveness of Learning Neural Networks: From Accessible States and Robust Ensembles to Basic Algorithmic Schemes
• The statistics of critical points of Gaussian fields on large-dimensional spaces
• Properties of equilibria and glassy phases of the random Lotka-Volterra model with demographic noise
• Effective potential in glassy systems: theory and simulations
• The spherical 2+p spin glass model: an analytically solvable model with a glass-to-glass transition
• Fragile vs strong liquids: a saddles ruled scenario
• The spherical $2+p$ spin glass model: an exactly solvable model for glass to spin-glass transition
• Rethinking mean-field glassy dynamics and its relation with the energy landscape: the awkward case of the spherical mixed p-spin model
• Dynamical TAP approach to mean field glassy systems
• Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions
• Unveiling the structure of wide flat minima in neural networks
• Gradient descent dynamics in the mixed $p$-spin spherical model: finite size simulation and comparison with mean-field integration
• On weak ergodicity breaking in mean-field spin glasses
• How to count in hierarchical landscapes: a 'full' solution to mean-field complexity
• The density of stationary points in a high-dimensional random energy landscape and the onset of glassy behaviour
• Bose-Einstein-Like condensation of deformed random matrix: A replica approach
• When is the average number of saddle points typical?
• The Threshold Energy of Low Temperature Langevin Dynamics for Pure Spherical Spin Glasses

Cited by in corpus (3)

• On the topology of solutions to random continuous constraint satisfaction problems
• Rare Trajectories in a Prototypical Mean-field Disordered Model: Insights into Landscape and Instantons
• Rényi complexity in mean-field disordered systems