Landscape complexity beyond invariance and the elastic manifold

DOI10.1002/CPA.22146MaRDI QIDQ6141981zbMATH OpenOpenAlexFDO

Authors Gerard Ben Arous, P. Bourgade, Benjamin Mckenna

Publication date 23 January 2024

Published in Communications on Pure and Applied Mathematics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2105.05051

Mathematics Subject Classification ID

Statistical mechanics, structure of matter (82-XX) Mechanics of deformable solids (74-XX)

Abstract: This paper characterizes the annealed, topological complexity (both of total critical points and of local minima) of the elastic manifold. This classical model of a disordered elastic system captures point configurations with self-interactions in a random medium. We establish the simple-vs.-glassy phase diagram in the model parameters, with these phases separated by a physical boundary known as the Larkin mass, confirming formulas of Fyodorov and Le Doussal. One essential, dynamical, step of the proof also applies to a general signal-to-noise model of soft spins in an anisotropic well, for which we prove a negative-second-moment threshold distinguishing positive from zero complexity. A universal near-critical behavior appears within this phase portrait, namely quadratic near-critical vanishing of the complexity of total critical points, and cubic near-critical vanishing of the complexity of local minima. These two models serve as a paradigm of complexity calculations for Gaussian landscapes exhibiting few distributional symmetries, i.e. beyond the invariant setting. The two main inputs for the proof are determinant asymptotics for non-invariant random matrices from our companion paper [Ben Arous, Bourgade, McKenna 2021], and the atypical convexity and integrability of the limiting variational problems.

Cites work

• scientific article; zbMATH DE number 3137757 (Why is no real title available?)
• scientific article; zbMATH DE number 527331 (Why is no real title available?)
• A spin glass model for the loss surfaces of generative adversarial networks
• Addition of certain non-commuting random variables
• Classical particle in a box with random potential: exploiting rotational symmetry of replicated Hamiltonian
• Complexity of Gaussian random fields with isotropic increments
• Complexity of random energy landscapes, glass transition, and absolute value of the spectral determinant of random matrices
• Complexity of random smooth functions on the high-dimensional sphere
• Concentration of the spectral measure for large matrices
• Distribution of rare saddles in the p -spin energy landscape
• Dyson Brownian motion for general \(\beta\) and potential at the edge
• Exponential growth of random determinants beyond invariance
• Exponential number of equilibria and depinning threshold for a directed polymer in a random potential
• Geometry and temperature chaos in mixed spherical spin glasses at low temperature: the perturbative regime
• Large deviations for extreme eigenvalues of deformed Wigner random matrices
• Large deviations for the largest eigenvalue of the sum of two random matrices
• Level Sets and Extrema of Random Processes and Fields
• Local deformed semicircle law and complete delocalization for Wigner matrices with random potential
• Location of the spectrum of Kronecker random matrices
• Manifolds pinned by a high-dimensional random landscape: Hessian at the global energy minimum
• Mathematical Analysis of Random Noise
• Mathematical Analysis of Random Noise
• Mean number and correlation function of critical points of isotropic Gaussian fields and some results on GOE random matrices
• Nonlinear analogue of the May-Wigner instability transition
• On the average number of real roots of a random algebraic equation
• On the free convolution with a semi-circular distribution
• On the support of the free additive convolution
• On universality of local edge regime for the deformed Gaussian unitary ensemble
• Operator-valued Semicircular Elements: Solving A Quadratic Matrix Equation with Positivity Constraints
• Random Fields and Geometry
• Random matrices and complexity of spin glasses
• Real Analysis and Probability
• Replica symmetry breaking condition exposed by random matrix calculation of landscape complexity
• Stability of the matrix Dyson equation and random matrices with correlations
• Statistical mechanics of a single particle in a multiscale random potential: Parisi landscapes in finite-dimensional Euclidean spaces
• TAP free energy, spin glasses and variational inference
• The complexity of spherical p-spin models: a second moment approach
• The landscape of the spiked tensor model
• The loss surfaces of neural networks with general activation functions
• The statistical analysis of a random, moving surface
• Topology trivialization and large deviations for the minimum in the simplest random optimization
• Triviality of the geometry of mixed \(p\)-spin spherical Hamiltonians with external field

Cited in

(1)

• On the expected number of critical points of locally isotropic Gaussian random fields

This page was built for publication: Landscape complexity beyond invariance and the elastic manifold

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6141981)