Image de couverture de livre

Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Castin, Valérie, Nadjahi, Kimia, Ablin, Pierre, Peyré, Gabriel
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning 68T07
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

A Unified Perspective on the Dynamics of Deep Transformers
par: Castin, Valérie, et autres
Publié: (2025)

How Smooth Is Attention?
par: Castin, Valérie, et autres
Publié: (2023)

FedRot-LoRA: Mitigating Rotational Misalignment in Federated LoRA
par: Zhang, Haoran, et autres
Publié: (2026)

A Generalization Bound for a Family of Implicit Networks
par: Fung, Samy Wu, et autres
Publié: (2024)

Evaluating Embedding Generalization: How LLMs, LoRA, and SLERP Shape Representational Geometry
par: Kabane, Siyaxolisa
Publié: (2025)

A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings
par: Hosen, Md Millat
Publié: (2025)

On The Convergence of Euler Discretization of Finite-Time Convergent Gradient Flows
par: Zhang, Siqi, et autres
Publié: (2020)

LoRA meets Riemannion: Muon Optimizer for Parametrization-independent Low-Rank Adapters
par: Bogachev, Vladimir, et autres
Publié: (2025)

Exploring Efficient Learning of Small BERT Networks with LoRA and DoRA
par: Frees, Daniel, et autres
Publié: (2025)

QuAILoRA: Quantization-Aware Initialization for LoRA
par: Lawton, Neal, et autres
Publié: (2024)

Super-fast Rates of Convergence for Neural Network Classifiers under the Hard Margin Condition
par: Tepakbong, Nathanael, et autres
Publié: (2025)

Influence-Inspired Spectral Rotations for Extreme Low-Bit LLM Quantization
par: Pavlov, Gorgi
Publié: (2026)

From Features to Graphs: Exploring Graph Structures and Pairwise Interactions via GNNs
par: Yamchote, Phaphontee, et autres
Publié: (2025)

The Inhibitor: ReLU and Addition-Based Attention for Efficient Transformers under Fully Homomorphic Encryption on the Torus
par: Brännvall, Rickard, et autres
Publié: (2023)

Convergence of Continuous Normalizing Flows for Learning Probability Distributions
par: Gao, Yuan, et autres
Publié: (2024)

The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
par: Bastounis, Alexander, et autres
Publié: (2023)

Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
par: Yi, Zeji, et autres
Publié: (2026)

Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
par: Liu, Qiang, et autres
Publié: (2026)

Flow matching on homogeneous spaces
par: Ruscelli, Francesco
Publié: (2026)

Training-Free Generative Sampling via Moment-Matched Score Smoothing
par: Yao, Zhenyu, et autres
Publié: (2026)

Generative Design of Ship Propellers using Conditional Flow Matching
par: Kruger, Patrick, et autres
Publié: (2026)

Beyond the Class Subspace: Teacher-Guided Training for Reliable Out-of-Distribution Detection in Single-Domain Models
par: Yang, Hong, et autres
Publié: (2026)

TabPFN for Zero-shot Parametric Engineering Design Generation
par: Wang, Ke, et autres
Publié: (2026)

Adynamical systems view of training generativemodels and the memorization phenomenon
par: Athreya, Siva, et autres
Publié: (2026)

Wave-Attractor-Tree: A Hierarchical Binary Tree Reduction Architecture for Efficient Sequence Modeling
par: Berezkin, Igor
Publié: (2026)

Graph-Conditional Flow Matching for Relational Data Generation
par: Scassola, Davide, et autres
Publié: (2025)

Feature Learning Beyond the Edge of Stability
par: Terjék, Dávid
Publié: (2025)

ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
par: Liu, Qiang, et autres
Publié: (2024)

Optimizing Basis Function Selection in Constructive Wavelet Neural Networks and Its Applications
par: Huang, Dunsheng, et autres
Publié: (2025)

A Teacher-Student Perspective on the Dynamics of Learning Near the Optimal Point
par: Couto, Carlos, et autres
Publié: (2025)

A Comprehensive View of Personalized Federated Learning on Heterogeneous Clinical Datasets
par: Tavakoli, Fatemeh, et autres
Publié: (2023)

Closed-Form Feedback-Free Learning with Forward Projection
par: O'Shea, Robert, et autres
Publié: (2025)

Markov Chain Estimation with In-Context Learning
par: Lepage, Simon, et autres
Publié: (2025)

Structured Knowledge Accumulation: The Principle of Entropic Least Action in Forward-Only Neural Learning
par: Quantiota, Bouarfa Mahi
Publié: (2025)

Deep Learning and Transfer Learning Architectures for English Premier League Player Performance Forecasting
par: Frees, Daniel, et autres
Publié: (2024)

Improving Fairness and Mitigating MADness in Generative Models
par: Mayer, Paul, et autres
Publié: (2024)

Cooperative Multi-Agent Deep Reinforcement Learning in Content Ranking Optimization
par: Qin, Zhou, et autres
Publié: (2024)

Stability Analysis of Equivariant Convolutional Representations Through The Lens of Equivariant Multi-layered CKNs
par: Chowdhury, Soutrik Roy
Publié: (2024)

Iterative Orthogonalization Scaling Laws
par: Selvaraj, Devan
Publié: (2025)

MLPs at the EOC: Spectrum of the NTK
par: Terjék, Dávid, et autres
Publié: (2025)