Imagen de Portada

An Augmented Backward-Corrected Projector Splitting Integrator for Dynamical Low-Rank Training

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kusch, Jonas, Schotthöfer, Steffen, Walter, Alexandra
Formato:	Preprint
Publicado:	2025
Materias:	Numerical Analysis Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks
por: Schotthöfer, Steffen, et al.
Publicado: (2025)

Geometry-aware training of factorized layers in tensor Tucker format
por: Zangrando, Emanuele, et al.
Publicado: (2023)

GeoLoRA: Geometric integration for parameter efficient fine-tuning
por: Schotthöfer, Steffen, et al.
Publicado: (2024)

Construction of high-order conservative basis-update and Galerkin dynamical low-rank integrators
por: Einkemmer, Lukas, et al.
Publicado: (2023)

Structure-preserving neural networks for the regularized entropy-based closure of the Boltzmann moment system
por: Schotthöfer, Steffen, et al.
Publicado: (2024)

A geometric framework for momentum-based optimizers for low-rank training
por: Schotthöfer, Steffen, et al.
Publicado: (2025)

Sketching Low-Rank Plus Diagonal Matrices
por: Fernandez, Andres, et al.
Publicado: (2025)

Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees
por: Schotthöfer, Steffen, et al.
Publicado: (2024)

Data-Driven Filtering of the Spherical Harmonics Method
por: Plumridge, Benjamin, et al.
Publicado: (2025)

Structured Variational $D$-Decomposition for Accurate and Stable Low-Rank Approximation
por: Katende, Ronald
Publicado: (2025)

Operator SVD with Neural Networks via Nested Low-Rank Approximation
por: Ryu, J. Jon, et al.
Publicado: (2024)

Nonconvex Approach for Sparse and Low-Rank Constrained Models with Dual Momentum
por: Wu, Cho-Ying, et al.
Publicado: (2019)

Provable Emergence of Deep Neural Collapse and Low-Rank Bias in $L^2$-Regularized Nonlinear Networks
por: Zangrando, Emanuele, et al.
Publicado: (2024)

Low-Rank Adversarial PGD Attack
por: Savostianova, Dayana, et al.
Publicado: (2024)

Low-Rank Approximation, Adaptation, and Other Tales
por: Lu, Jun
Publicado: (2024)

Artifacts of Numerical Integration in Learning Dynamical Systems
por: Lu, Bing-Ze, et al.
Publicado: (2025)

DeepRitzSplit Neural Operator for Phase-Field Models via Energy Splitting
por: Huang, Chih-Kang, et al.
Publicado: (2026)

Lyapunov Analysis For Monotonically Forward-Backward Accelerated Algorithms
por: Fu, Mingwei, et al.
Publicado: (2024)

A Parallel, Energy-Stable Low-Rank Integrator for Nonlinear Multi-Scale Thermal Radiative Transfer
por: Patwardhan, Chinmay, et al.
Publicado: (2025)

$ε$-rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics
por: Yang, Jiang, et al.
Publicado: (2024)

A Family of Controllable Momentum Coefficients for Forward-Backward Accelerated Algorithms
por: Fu, Mingwei, et al.
Publicado: (2025)

Random Subspace Cubic-Regularization Methods, with Applications to Low-Rank Functions
por: Cartis, Coralia, et al.
Publicado: (2025)

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration
por: Pourkamali-Anaraki, Farhad
Publicado: (2026)

Beyond Derivative Pathology of PINNs: Variable Splitting Strategy with Convergence Analysis
por: Park, Yesom, et al.
Publicado: (2024)

An Accelerated Newton-GMRES Method for Multilinear PageRank
por: Boubekraoui, Maryam, et al.
Publicado: (2025)

Kinetic Langevin Splitting Schemes for Constrained Sampling
por: Chada, Neil K., et al.
Publicado: (2026)

Windowing Regularization Techniques for Unsteady Aerodynamic Shape Optimization
por: Schotthöfer, Steffen, et al.
Publicado: (2024)

Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
por: Liu, Taowen, et al.
Publicado: (2025)

Accelerating Power Method with Fast Sketching for Stronger Low-Rank Approximation
por: Chenakkod, Shabarish, et al.
Publicado: (2026)

Training-Free Looped Transformers
por: Chen, Lizhang, et al.
Publicado: (2026)

Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
por: Li, Guoming, et al.
Publicado: (2026)

Quantum Harmonic Analysis and the Structure in Data: Augmentation
por: Doerfler, Monika, et al.
Publicado: (2025)

Neural Low-Discrepancy Sequences
por: Van Huffel, Michael Etienne, et al.
Publicado: (2025)

Structure-Preserving Operator Learning: Modeling the Collision Operator of Kinetic Equations
por: Lee, Jae Yong, et al.
Publicado: (2024)

Ensemble Score Filtering for Real-Data Energy Consumption Forecast Correction
por: Hu, Ruoyu, et al.
Publicado: (2026)

Training Hamiltonian neural networks without backpropagation
por: Rahma, Atamert, et al.
Publicado: (2024)

Bayesian Quadrature: Gaussian Processes for Integration
por: Mahsereci, Maren, et al.
Publicado: (2026)

Augmented data and neural networks for robust epidemic forecasting: application to COVID-19 in Italy
por: Dimarco, Giacomo, et al.
Publicado: (2025)

Multi-Level Monte Carlo Training of Neural Operators
por: Rowbottom, James, et al.
Publicado: (2025)

Generative Feature Training of Thin 2-Layer Networks
por: Hertrich, Johannes, et al.
Publicado: (2024)