Random matrices and complexity of spin glasses
From MaRDI portal
Publication:4904469
Abstract: We give an asymptotic evaluation of the complexity of spherical p-spin spin-glass models via random matrix theory. This study enables us to obtain detailed information about the bottom of the energy landscape, including the absolute minimum (the ground state), the other local minima, and describe an interesting layered structure of the low critical values for the Hamiltonians of these models. We also show that our approach allows us to compute the related TAP-complexity and extend the results known in the physics literature. As an independent tool, we prove a LDP for the k-th largest eigenvalue of the GOE, extending the results of Ben Arous, Dembo and Guionnett (2001).
Recommendations
- Complexity of random smooth functions on the high-dimensional sphere
- Concentration of the complexity of spherical pure \(p\)-spin models at arbitrary energies
- Complexity of random energy landscapes, glass transition, and absolute value of the spectral determinant of random matrices
- Recent results on the energy landscapes of mean field spin glasses
- The complexity of spherical \(p\)-spin models: a second moment approach
Cites work
- scientific article; zbMATH DE number 1464566 (Why is no real title available?)
- 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
- Free energy of the spherical mean field model
- Large deviations for Wigner's law and Voiculescu's non-commutative entropy
- Level Sets and Extrema of Random Processes and Fields
- On the overlap in the multiple spherical SK models
- Phase space geometry and slow dynamics
- Random Fields and Geometry
- Replica symmetry breaking condition exposed by random matrix calculation of landscape complexity
- Universality in Random Matrix Theory for orthogonal and symplectic ensembles
Cited in
(only showing first 100 items - show all)- Optimization of mean-field spin glasses
- A CLT concerning critical points of random functions on a Euclidean space
- Singularities of Gaussian random maps into the plane
- Exponential number of equilibria and depinning threshold for a directed polymer in a random potential
- Exponential growth of random determinants beyond invariance
- Large deviations for the largest eigenvalues and eigenvectors of spiked Gaussian random matrices
- A note on mixed matrix moments for the complex Ginibre ensemble
- Sum rules via large deviations
- On the Marchenko–Pastur law in analog bipartite spin-glasses
- Asymptotic topology of excursion and nodal sets of Gaussian random fields
- Almost sure convergence in quantum spin glasses
- Localization in the discrete non-linear Schrödinger equation and geometric properties of the microcanonical surface
- Expected number of critical points of random holomorphic sections over complex projective space
- Sparse random tensors: concentration, regularization and applications
- Approximate ground states of hypercube spin glasses are near corners
- On the spectral gap of spherical spin glass dynamics
- Complexity of random energy landscapes, glass transition, and absolute value of the spectral determinant of random matrices
- A spin glass model for the loss surfaces of generative adversarial networks
- The geometry of the Gibbs measure of pure spherical spin glasses
- The complexity of spherical \(p\)-spin models: a second moment approach
- Extreme value statistics of correlated random variables: a pedagogical review
- TAP free energy, spin glasses and variational inference
- Expected topology of random real algebraic submanifolds
- Melonic dominance and the largest eigenvalue of a large random tensor
- Simultaneous large deviations for the shape of Young diagrams associated with random words
- Dynamics for spherical spin glasses: disorder dependent initial conditions
- First-order methods almost always avoid strict saddle points
- Dynamics of mean field spin glasses on short and long timescales
- Hessian spectrum at the global minimum of high-dimensional random landscapes
- Statistically optimal and computationally efficient low rank tensor completion from noisy entries
- Temperature chaos in some spherical mixed \(p\)-spin models
- Algorithmic thresholds for tensor PCA
- On the optimization landscape of tensor decompositions
- Mean-field equations for spin models with orthogonal interaction matrices
- The loss surfaces of neural networks with general activation functions
- Free energy fluctuations of the two-spin spherical SK model at critical temperature
- Local minima in disordered mean-field ferromagnets
- Kac-Rice formulas and the number of solutions of parametrized systems of polynomial equations
- Topology trivialization transition in random non-gradient autonomous ODEs on a sphere
- Approximate ultrametricity for random measures and applications to spin glasses
- Gaussian fluctuations of the determinant of Wigner matrices
- The TAP-Plefka variational principle for the spherical SK model
- Expected number and height distribution of critical points of smooth isotropic Gaussian random fields
- The free energy of spherical pure \(p\)-spin models: computation from the TAP approach
- Nonlinear analogue of the May-Wigner instability transition
- Parisi formula, disorder chaos and fluctuation for the ground state energy in the spherical mixed \(p\)-spin models
- Matrix norms and rapid mixing for spin systems
- Manifolds pinned by a high-dimensional random landscape: Hessian at the global energy minimum
- Dynamical mean-field theory and aging dynamics
- On the number of connected components of random algebraic hypersurfaces
- Zero-temperature dynamics in the dilute Curie-Weiss model
- The algorithmic hardness threshold for continuous random energy models
- Optimization landscape in the simplest constrained random least-square problem
- The extremal process of critical points of the pure \(p\)-spin spherical spin Glass model
- Notes on computational hardness of hypothesis testing: predictions using the low-degree likelihood ratio
- Triviality of the geometry of mixed \(p\)-spin spherical Hamiltonians with external field
- Euclidean random matrices: solved and open problems
- Spectral norm of a symmetric tensor and its computation
- Spectral gap estimates in mean field spin glasses
- Notes on computational-to-statistical gaps: predictions using statistical physics
- Complexity of random smooth functions on the high-dimensional sphere
- Topology trivialization and large deviations for the minimum in the simplest random optimization
- Statistical limits of spiked tensor models
- On the energy landscape of spherical spin glasses
- Bounding flows for spherical spin glass dynamics
- Fluctuations of the free energy of the spherical Sherrington-Kirkpatrick model with ferromagnetic interaction
- On properties of the spherical mixed vector \(p\)-spin model
- On the energy landscape of the mixed even \(p\)-spin model
- The real Ginibre ensemble with \(k=O(n)\) real eigenvalues
- Free energy and complexity of spherical bipartite models
- Thouless-Anderson-Palmer equations for the Ghatak-Sherrington mean field spin glass model
- May-Wigner transition in large random dynamical systems
- Existence of two-step replica symmetry breaking for the spherical mixed \(p\)-spin glass at zero temperature
- Statistical mechanics of the maximum-average submatrix problem
- Sharp complexity asymptotics and topological trivialization for the (p, k) spiked tensor model
- Superposition of random plane waves in high spatial dimensions: Random matrix approach to landscape complexity
- Shattering versus metastability in spin glasses
- Generalized TAP Free Energy
- Usefulness of signed eigenvalue/vector distributions of random tensors
- Statistics of stationary points of random finite polynomial potentials
- How many eigenvalues of a random symmetric tensor are real?
- TAP approach for multispecies spherical spin glasses II: the free energy of the pure models
- Distribution of rare saddles in the p -spin energy landscape
- Analytic continuation over complex landscapes
- An Elementary mean-field approach to the spectral densities of random matrix ensembles
- Superposition of Random Plane Waves in High Spatial Dimensions: Random Matrix Approach to Landscape Complexity
- Hardness of Random Optimization Problems for Boolean Circuits, Low-Degree Polynomials, and Langevin Dynamics
- Landscape complexity beyond invariance and the elastic manifold
- The ground state energy and concentration of complexity in spherical bipartite models
- Universal halting times in optimization and machine learning
- A supersymmetric SYK model with a curious low energy behavior
- Quenched complexity of equilibria for asymmetric generalized Lotka–Volterra equations
- Complexity of Gaussian random fields with isotropic increments
- Optimizing mean field spin glasses with external field
- Dense Hebbian neural networks: a replica symmetric picture of unsupervised learning
- Black holes and the loss landscape in machine learning
- Marchenko–Pastur law with relaxed independence conditions
- Linear low energy excitations in fully-connected models of glasses
- Signed distributions of real tensor eigenvectors of Gaussian tensor model via a four-Fermi theory
- The geometry of near ground states in Gaussian polymer models
This page was built for publication: Random matrices and complexity of spin glasses
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4904469)
