Imagen de Portada

NeuraLSP: An Efficient and Rigorous Neural Left Singular Subspace Preconditioner for Conjugate Gradient Methods

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Benanti, Alexander, Han, Xi, Qin, Hong
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UGrid: An Efficient-And-Rigorous Neural Multigrid Solver for Linear PDEs
por: Han, Xi, et al.
Publicado: (2024)

GeoMaNO: Geometric Mamba Neural Operator for Partial Differential Equations
por: Han, Xi, et al.
Publicado: (2025)

Lotus: Efficient LLM Training by Randomized Low-Rank Gradient Projection with Adaptive Subspace Switching
por: Miao, Tianhao, et al.
Publicado: (2026)

Generative modeling of Sparse Approximate Inverse Preconditioners
por: Li, Mou, et al.
Publicado: (2024)

Logic Sketch Prompting (LSP): A Deterministic and Interpretable Prompting Method
por: Tripathi, Satvik
Publicado: (2025)

Spectral Surgery: Training-Free Refinement of LoRA via Gradient-Guided Singular Value Reweighting
por: Tian, Zailong, et al.
Publicado: (2026)

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner
por: Eschenhagen, Runa, et al.
Publicado: (2025)

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks
por: Cloud, Alex, et al.
Publicado: (2024)

Sven: Singular Value Descent as a Computationally Efficient Natural Gradient Method
por: Bright-Thonney, Samuel, et al.
Publicado: (2026)

Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
por: Kim, Dongyoon, et al.
Publicado: (2025)

Enhancing Output Diversity Improves Conjugate Gradient-based Adversarial Attacks
por: Yamamura, Keiichiro, et al.
Publicado: (2024)

Communication-Efficient Federated Learning with Accelerated Client Gradient
por: Kim, Geeho, et al.
Publicado: (2022)

Dispelling the Curse of Singularities in Neural Network Optimizations
por: Cao, Hengjie, et al.
Publicado: (2026)

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
por: Wang, Hong, et al.
Publicado: (2024)

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
por: Tang, Xuan, et al.
Publicado: (2025)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
por: Li, Rui, et al.
Publicado: (2024)

Dynamic Low-rank Approximation of Full-Matrix Preconditioner for Training Generalized Linear Models
por: Matveeva, Tatyana, et al.
Publicado: (2025)

A Generalized Singular Value Theory for Neural Networks
por: Brown, Brian Charles, et al.
Publicado: (2026)

R-GTD: A Geometric Analysis of Gradient Temporal-Difference Learning in Singular Regimes
por: Na, Hyunjun, et al.
Publicado: (2026)

Exploring Gradient Subspaces: Addressing and Overcoming LoRA's Limitations in Federated Fine-Tuning of Large Language Models
por: Mahla, Navyansh, et al.
Publicado: (2024)

Adaptive Budget Allocation for Orthogonal-Subspace Adapter Tuning in LLMs Continual Learning
por: Wan, Zhiyi, et al.
Publicado: (2025)

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
por: Olteanu, Alexandra, et al.
Publicado: (2025)

Enhancing Deep Learning with Optimized Gradient Descent: Bridging Numerical Methods and Neural Network Training
por: Ma, Yuhan, et al.
Publicado: (2024)

Gradient Weight-normalized Low-rank Projection for Efficient LLM Training
por: Huang, Jia-Hong, et al.
Publicado: (2024)

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations
por: Marzari, Luca, et al.
Publicado: (2024)

Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data
por: Liu, Junkang, et al.
Publicado: (2026)

Efficient Utility-Preserving Machine Unlearning with Implicit Gradient Surgery
por: Zhou, Shiji, et al.
Publicado: (2025)

Towards Efficient Few-shot Graph Neural Architecture Search via Partitioning Gradient Contribution
por: Song, Wenhao, et al.
Publicado: (2025)

NeuralGrok: Accelerate Grokking by Neural Gradient Transformation
por: Zhou, Xinyu, et al.
Publicado: (2025)

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
por: Gu, Yuxian, et al.
Publicado: (2025)

Rethinking LoRA for Data Heterogeneous Federated Learning: Subspace and State Alignment
por: Peng, Hongyi, et al.
Publicado: (2026)

Gradient Correlation Subspace Learning against Catastrophic Forgetting
por: Dubnov, Tammuz, et al.
Publicado: (2024)

Axiomatization of Gradient Smoothing in Neural Networks
por: Zhou, Linjiang, et al.
Publicado: (2024)

Model Merging in the Essential Subspace
por: Li, Longhua, et al.
Publicado: (2026)

Robust and Efficient Zeroth-Order LLM Fine-Tuning via Adaptive Bayesian Subspace Optimizer
por: Feng, Jian, et al.
Publicado: (2026)

How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark
por: Qiu, Ruizhong, et al.
Publicado: (2024)

EigenLoRAx: Recycling Adapters to Find Principal Subspaces for Resource-Efficient Adaptation and Inference
por: Kaushik, Prakhar, et al.
Publicado: (2025)

Memory-Efficient LLM Training with Online Subspace Descent
por: Liang, Kaizhao, et al.
Publicado: (2024)

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
por: Hameed, Marawan Gamal Abdel, et al.
Publicado: (2024)

Conjugate Learning Theory: Uncovering the Mechanisms of Trainability and Generalization in Deep Neural Networks
por: Qi, Binchuan
Publicado: (2026)