Landscape complexity beyond invariance and the elastic manifold

DOI10.1002/CPA.22146arXiv2105.05051OpenAlexW3161311214MaRDI QIDQ6141981FDOQ6141981

Gerard Ben Arous, Benjamin Mckenna, P. Bourgade

Publication date: 23 January 2024

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

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.

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)

Cites Work

• Real Analysis and Probability
• Level Sets and Extrema of Random Processes and Fields
• Random Fields and Geometry
• On the average number of real roots of a random algebraic equation
• Classical particle in a box with random potential: exploiting rotational symmetry of replicated Hamiltonian
• Addition of certain non-commuting random variables
• Title not available (Why is that?)
• Mathematical Analysis of Random Noise
• Complexity of random energy landscapes, glass transition, and absolute value of the spectral determinant of random matrices
• On the support of the free additive convolution
• On the free convolution with a semi-circular distribution
• On universality of local edge regime for the deformed Gaussian unitary ensemble
• Random Matrices and Complexity of Spin Glasses
• Concentration of the spectral measure for large matrices
• The statistical analysis of a random, moving surface
• Mathematical Analysis of Random Noise
• Title not available (Why is that?)
• Geometry and Temperature Chaos in Mixed Spherical Spin Glasses at Low Temperature: The Perturbative Regime
• Operator-valued Semicircular Elements: Solving A Quadratic Matrix Equation with Positivity Constraints
• Complexity of random smooth functions on the high-dimensional sphere
• The complexity of spherical \(p\)-spin models: a second moment approach
• Stability of the matrix Dyson equation and random matrices with correlations
• Replica symmetry breaking condition exposed by random matrix calculation of landscape complexity
• Local deformed semicircle law and complete delocalization for Wigner matrices with random potential
• Statistical mechanics of a single particle in a multiscale random potential: Parisi landscapes in finite-dimensional Euclidean spaces
• The Landscape of the Spiked Tensor Model
• Exponential number of equilibria and depinning threshold for a directed polymer in a random potential
• Large deviations for the largest eigenvalue of the sum of two random matrices
• Dyson Brownian motion for general \(\beta\) and potential at the edge
• Exponential growth of random determinants beyond invariance
• Location of the spectrum of Kronecker random matrices
• Manifolds pinned by a high-dimensional random landscape: Hessian at the global energy minimum
• Topology trivialization and large deviations for the minimum in the simplest random optimization
• A spin glass model for the loss surfaces of generative adversarial networks
• Nonlinear analogue of the May−Wigner instability transition
• Large deviations for extreme eigenvalues of deformed Wigner random matrices
• Triviality of the geometry of mixed \(p\)-spin spherical Hamiltonians with external field
• TAP free energy, spin glasses and variational inference
• The loss surfaces of neural networks with general activation functions
• Mean number and correlation function of critical points of isotropic Gaussian fields and some results on GOE random matrices
• Complexity of Gaussian random fields with isotropic increments
• Distribution of rare saddles in the p -spin energy landscape

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)