Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA

DOI10.1007/S00440-026-01506-9MaRDI QIDQ7396383zbMATH OpenFDO

Authors Gerard Ben Arous, Cédric Gerbelot, Vanessa Piccolo

Publication date 2026

Published in Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00440-026-01506-9

Mathematics Subject Classification ID

Martingales with continuous parameter (60G44) Applications of stochastic analysis (to PDEs, etc.) (60H30) Parametric inference under constraints (62F30) Probability in computer science (algorithm analysis, random structures, phase transitions, etc.) (68Q87)

Cites work

• Aging of spherical spin glasses
• Algorithmic thresholds for tensor PCA
• An Introduction to Optimization on Smooth Manifolds
• Bounding flows for spherical spin glass dynamics
• Brownian motion, martingales, and stochastic calculus
• Cugliandolo-Kurchan equations for dynamics of spin-glasses
• Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification*
• Eigenvalues and Condition Numbers of Random Matrices
• Fast spectral algorithms from sum-of-squares proofs: tensor decomposition and planted sparse vectors
• Global optimization with orthogonality constraints via stochastic diffusion on manifold
• High-dimensional asymptotics of Langevin dynamics in spiked matrix models
• High‐dimensional limit theorems for SGD: Effective dynamics and critical scaling
• scientific article; zbMATH DE number 6125590 (Why is no real title available?)
• Long random matrices and tensor unfolding
• On the distribution of the largest eigenvalue in principal components analysis
• Online stochastic gradient descent on non-convex losses from high-dimensional inference
• Out-of-equilibrium dynamical mean-field equations for the perceptron model
• Phase transition in random tensors with multiple independent spikes
• Phase transition in the spiked random tensor with Rademacher prior
• Random matrices and complexity of spin glasses
• Rigorous dynamical mean field theory for stochastic gradient descent methods
• Sanov results for Glauber spin-glass dynamics
• Statistical Physics of Spin Glasses and Information Processing
• Statistical thresholds for tensor PCA
• Statistics on special manifolds
• The Kikuchi hierarchy and tensor PCA
• The landscape of the spiked tensor model

This page was built for publication: Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7396383)