Stochastic dynamical low-rank approximation in the context of machine learning

DOI10.1007/S10957-025-02892-1MaRDI QIDQ6874627zbMATH OpenFDO

Authors Arsen Hnatiuk, Jonas Kusch, Lisa Kusch, Nicolas R. Gauger, Andrea Walther

Publication date 15 January 2026

Published in Journal of Optimization Theory and Applications (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S10957-025-02892-1

zbMATH Keywords

deep neural networksdynamical low-rank approximation (DLRA)dynamical low-rank training (DLRT)machine learningstochastic gradient descent

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Methods of reduced gradient type (90C52) Stochastic learning and adaptive control (93E35)

Cites work

• A parallel rank-adaptive integrator for dynamical low-rank approximation
• A projector-splitting integrator for dynamical low-rank approximation
• A rank-adaptive robust integrator for dynamical low-rank approximation
• A robust second-order low-rank BUG integrator based on the midpoint rule
• An unconventional robust integrator for dynamical low-rank approximation
• Discretized dynamical low-rank approximation in the presence of small singular values
• Dynamical Low‐Rank Approximation
• Gradient Convergence in Gradient methods with Errors
• Optimization for data analysis
• Optimization methods for large-scale machine learning
• Projection methods for dynamical low-rank approximation of high-dimensional problems
• Riemannian optimization and its applications
• Second-order robust parallel integrators for dynamical low-rank approximation

Cited in

(1)

• An augmented backward-corrected projector splitting integrator for dynamical low-rank training

This page was built for publication: Stochastic dynamical low-rank approximation in the context of machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6874627)