Image de couverture de livre

A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sun, Zexuan, Raskutti, Garvesh
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Reliable and scalable variable importance estimation via warm-start and early stopping
par: Sun, Zexuan, et autres
Publié: (2024)

MinShap: A Modified Shapley Value Approach for Feature Selection
par: Zheng, Chenghui, et autres
Publié: (2026)

Online Localized Conformal Prediction
par: Lai, Yuheng, et autres
Publié: (2026)

Comparing Model-agnostic Feature Selection Methods through Relative Efficiency
par: Zheng, Chenghui, et autres
Publié: (2025)

Gaussian Process Inference Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits
par: Chen, Hao, et autres
Publié: (2021)

Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
par: Ding, Meng, et autres
Publié: (2024)

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
par: Zhou, Huichi, et autres
Publié: (2025)

A General Framework to Enhance Fine-tuning-based LLM Unlearning
par: Ren, Jie, et autres
Publié: (2025)

Analyzing the Effect of Noise in LLM Fine-tuning
par: Li, Lingfang, et autres
Publié: (2026)

Instance-dependent Early Stopping
par: Yuan, Suqin, et autres
Publié: (2025)

Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning
par: Chen, Sirui, et autres
Publié: (2026)

Statistical Early Stopping for Reasoning Models
par: Xie, Yangxinyu, et autres
Publié: (2026)

Loquetier: A Virtualized Multi-LoRA Framework for Unified LLM Fine-tuning and Serving
par: Zhang, Yuchen, et autres
Publié: (2025)

Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms
par: Xu, Tian, et autres
Publié: (2026)

Early Stopping Tabular In-Context Learning
par: Küken, Jaris, et autres
Publié: (2025)

Noisy Early Stopping for Noisy Labels
par: Toner, William, et autres
Publié: (2024)

BoostLLM: Boosting-inspired LLM Fine-tuning for Few-shot Tabular Classification
par: Wang, Yi-Siang, et autres
Publié: (2026)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
par: Kim, Minseon, et autres
Publié: (2025)

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
par: Youstra, Jack, et autres
Publié: (2025)

Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics
par: Li, Shiwei, et autres
Publié: (2025)

Early Stopping Based on Repeated Significance
par: Bax, Eric, et autres
Publié: (2024)

The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
par: Liang, Qiyao, et autres
Publié: (2026)

QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
par: Lee, Doyeon, et autres
Publié: (2026)

PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning
par: Wang, Qibin, et autres
Publié: (2024)

Rethinking Early Stopping: Refine, Then Calibrate
par: Berta, Eugène, et autres
Publié: (2025)

Fine-tuning Timeseries Predictors Using Reinforcement Learning
par: Cazaux, Hugo, et autres
Publié: (2026)

Deep Fair Learning: A Unified Framework for Fine-tuning Representations with Sufficient Networks
par: Shi, Enze, et autres
Publié: (2025)

Why LLM Safety Guardrails Collapse After Fine-tuning: A Similarity Analysis Between Alignment and Fine-tuning Datasets
par: Hsiung, Lei, et autres
Publié: (2025)

Outlier-weighed Layerwise Sampling for LLM Fine-tuning
par: Li, Pengxiang, et autres
Publié: (2024)

Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
par: Luo, Yu, et autres
Publié: (2026)

Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
par: Wang, Haozhong, et autres
Publié: (2026)

Two-stage LLM Fine-tuning with Less Specialization and More Generalization
par: Wang, Yihan, et autres
Publié: (2022)

When to Stop Federated Learning: Zero-Shot Generation of Synthetic Validation Data with Generative AI for Early Stopping
par: Lee, Youngjoon, et autres
Publié: (2025)

Non-Asymptotic Analysis of (Sticky) Track-and-Stop
par: Poiani, Riccardo, et autres
Publié: (2025)

Relational Knowledge Distillation Using Fine-tuned Function Vectors
par: Kang, Andrea, et autres
Publié: (2026)

ESPO: Early-Stopping Proximal Policy Optimization
par: Li, Zihang, et autres
Publié: (2026)

Convex SGD: Generalization Without Early Stopping
par: Hendrickx, Julien, et autres
Publié: (2024)

Benefits of Early Stopping in Gradient Descent for Overparameterized Logistic Regression
par: Wu, Jingfeng, et autres
Publié: (2025)

GRADSTOP: Early Stopping of Gradient Descent via Posterior Sampling
par: Jamshidi, Arash, et autres
Publié: (2025)

Early Stopping Against Label Noise Without Validation Data
par: Yuan, Suqin, et autres
Publié: (2025)