Imagen de Portada

Global Low-Rank, Local Full-Rank: The Holographic Encoding of Learned Algorithms

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Xu, Yongzhong
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

SwitchLoRA: Switched Low-Rank Adaptation Can Learn Full-Rank Information
por: Zhou, Kaiye, et al.
Publicado: (2024)

Low-Dimensional and Transversely Curved Optimization Dynamics in Grokking
por: Xu, Yongzhong
Publicado: (2026)

Optimizer-Induced Low-Dimensional Drift and Transverse Dynamics in Transformer Training
por: Xu, Yongzhong
Publicado: (2026)

Spectral Edge Dynamics Reveal Functional Modes of Learning
por: Xu, Yongzhong
Publicado: (2026)

Low-Dimensional Execution Manifolds in Transformer Learning Dynamics: Evidence from Modular Arithmetic Tasks
por: Xu, Yongzhong
Publicado: (2026)

Early-Warning Signals of Grokking via Loss-Landscape Geometry
por: Xu, Yongzhong
Publicado: (2026)

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
por: Xu, Yongzhong
Publicado: (2026)

The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure
por: Xu, Yongzhong
Publicado: (2026)

Spectral Probe-Circuits: A Three-Step Recipe for Identifying Attention-Head Circuits in Pretrained Transformers
por: Xu, Yongzhong
Publicado: (2026)

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
por: Xu, Yongzhong
Publicado: (2026)

Spectral Edge Dynamics: An Analytical-Empirical Study of Phase Transitions in Neural Network Training
por: Xu, Yongzhong
Publicado: (2026)

When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures
por: Xu, Yongzhong
Publicado: (2026)

Feature Repulsion and Spectral Lock-in: An Empirical Study of Two-Layer Network Grokking
por: Xu, Yongzhong
Publicado: (2026)

Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training
por: Zhang, Chengqian, et al.
Publicado: (2026)

Low-Rank Compression of Language Models via Differentiable Rank Selection
por: Sundrani, Sidhant, et al.
Publicado: (2025)

Riemannian Networks over Full-Rank Correlation Matrices
por: Chen, Ziheng, et al.
Publicado: (2026)

DEL-Ranking: Ranking-Correction Denoising Framework for Elucidating Molecular Affinities in DNA-Encoded Libraries
por: Cao, Hanqun, et al.
Publicado: (2024)

Ranking-aware Reinforcement Learning for Ordinal Ranking
por: Hao, Aiming, et al.
Publicado: (2026)

Rank-1 LoRAs Encode Interpretable Reasoning Signals
por: Ward, Jake, et al.
Publicado: (2025)

Energy-Structured Low-Rank Adaptation for Continual Learning
por: Li, Longhua, et al.
Publicado: (2026)

PLAN: Proactive Low-Rank Allocation for Continual Learning
por: Wang, Xiequn, et al.
Publicado: (2025)

Toward Learning POMDPs Beyond Full-Rank Actions and State Observability
por: Shaw, Seiji, et al.
Publicado: (2026)

Mixture-of-Subspaces in Low-Rank Adaptation
por: Wu, Taiqiang, et al.
Publicado: (2024)

Towards Symmetric Low-Rank Adapters
por: Panoutsos, Tales, et al.
Publicado: (2025)

The Primacy of Magnitude in Low-Rank Adaptation
por: Zhang, Zicheng, et al.
Publicado: (2025)

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
por: Zhuang, Yuan, et al.
Publicado: (2026)

FRoD: Full-Rank Efficient Fine-Tuning with Rotational Degrees for Fast Convergence
por: Wan, Guoan, et al.
Publicado: (2025)

Communication-Efficient Federated Low-Rank Update Algorithm and its Connection to Implicit Regularization
por: Park, Haemin, et al.
Publicado: (2024)

Preference Learning Algorithms Do Not Learn Preference Rankings
por: Chen, Angelica, et al.
Publicado: (2024)

Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
por: Xu, Alec S., et al.
Publicado: (2026)

Polynomial Expansion Rank Adaptation: Enhancing Low-Rank Fine-Tuning with High-Order Interactions
por: Zhang, Wenhao, et al.
Publicado: (2026)

MoR: Mixture of Ranks for Low-Rank Adaptation Tuning
por: Tang, Chuanyu, et al.
Publicado: (2024)

Stable-LoRA: Stabilizing Feature Learning of Low-Rank Adaptation
por: Wu, Yize, et al.
Publicado: (2026)

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
por: Zhang, Jiaying, et al.
Publicado: (2026)

Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning
por: Rozada, Sergio, et al.
Publicado: (2022)

Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning
por: Li, Jiaqi, et al.
Publicado: (2023)

Optimal Policy Sparsification and Low Rank Decomposition for Deep Reinforcement Learning
por: Goddla, Vikram
Publicado: (2024)

Probe-Free Low-Rank Activation Intervention
por: Jiang, Chonghe, et al.
Publicado: (2025)

Low-Rank MDPs with Continuous Action Spaces
por: Bennett, Andrew, et al.
Publicado: (2023)

Low Rank Gradients and Where to Find Them
por: Sonthalia, Rishi, et al.
Publicado: (2025)