Peer-reviewedLicence not statedProbability Theory and Related Fields
Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA
4 affiliations
- 1Courant Institute of Mathematical Sciences, New York University, New York, USA
- 2CIMS - Courant Institute of Mathematical Sciences [New York] (251, Mercier Street, New York, NY 10012 - United States)
- 3Unité de Mathématiques Pures et Appliquées (UMPA), ENS, Lyon, France
- 4UMPA-ENSL - Unité de Mathématiques Pures et Appliquées (France)
Related
- Averaged Annealed Markov Chains Achieve the Algorithmic Threshold for Tensor PCA, Part II: Langevin Dynamics
- Global Convergence of Third-Order Langevin Dynamics for Non-Convex Optimization via Simulated Annealing
- Stochastic Gradient Descent in High Dimensions for Multi‐Spiked Tensor PCA
- High-dimensional extreme eigenvalue problems: low-rank tensor parametrization and optimization
- Tensor-Train Weak SINDy: Identifying High-Dimensional Nonlinear Dynamics
BibTeX
@article{arous2026langevin,
title = {{Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA}},
author = {Gérard Ben Arous and Cédric Gerbelot and Vanessa Piccolo},
journal = {Probability Theory and Related Fields},
year = {2026},
month = jul,
doi = {10.1007/s00440-026-01506-9},
url = {https://arxiv.org/abs/2408.06401},
}
RIS
TY - JOUR
TI - Langevin dynamics for high-dimensional optimization: the case of multi-spiked tensor PCA
AU - Gérard Ben Arous
AU - Cédric Gerbelot
AU - Vanessa Piccolo
PY - 2026
DA - 2026/07/27
JO - Probability Theory and Related Fields
DO - 10.1007/s00440-026-01506-9
UR - https://arxiv.org/abs/2408.06401
SN - 0178-8051
SN - 1432-2064
ER -