Cover Image

Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ding, Meng, Sharma, Rohan, Chen, Changyou, Xu, Jinhui, Ji, Kaiyi
Format:	Preprint
Published:	2024
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Discriminative Adversarial Unlearning
by: Sharma, Rohan, et al.
Published: (2024)

Provable Effects of Data Replay in Continual Learning: A Feature Learning Perspective
by: Ding, Meng, et al.
Published: (2026)

Understanding Forgetting in Continual Learning with Linear Regression
by: Ding, Meng, et al.
Published: (2024)

Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements
by: Zhou, Shijie, et al.
Published: (2024)

Understanding Private Learning From Feature Perspective
by: Ding, Meng, et al.
Published: (2025)

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs
by: Ban, Hao, et al.
Published: (2025)

Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
by: Tomihari, Akiyoshi, et al.
Published: (2024)

A General Framework to Enhance Fine-tuning-based LLM Unlearning
by: Ren, Jie, et al.
Published: (2025)

Lower Complexity Bounds for Nonconvex-Strongly-Convex Bilevel Optimization with First-Order Oracles
by: Ji, Kaiyi
Published: (2025)

Theoretical Study of Conflict-Avoidant Multi-Objective Reinforcement Learning
by: Wang, Yudan, et al.
Published: (2024)

Fair Resource Allocation in Multi-Task Learning
by: Ban, Hao, et al.
Published: (2024)

Turning Back Without Forgetting: Selective Backward Refinement for Parameter-Efficient Continual Learning
by: Tiwari, Anushka, et al.
Published: (2026)

Distribution Preference Optimization: A Fine-grained Perspective for LLM Unlearning
by: Qin, Kai, et al.
Published: (2025)

FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data
by: Xu, Binqian, et al.
Published: (2024)

Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
by: Chien, Eli, et al.
Published: (2024)

A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization
by: Sun, Zexuan, et al.
Published: (2026)

Rethinking Safety in LLM Fine-tuning: An Optimization Perspective
by: Kim, Minseon, et al.
Published: (2025)

Information Guided Regularization for Fine-tuning Language Models
by: Sharma, Mandar, et al.
Published: (2024)

Exact Unlearning from Proxies Induces Closeness Guarantees on Approximate Unlearning
by: Dine, Virgile, et al.
Published: (2026)

LoRA vs. Full Fine-Tuning: A Theoretical Perspective
by: Zindari, Ali, et al.
Published: (2026)

The Blessing of Dimensionality in LLM Fine-tuning: A Variance-Curvature Perspective
by: Liang, Qiyao, et al.
Published: (2026)

Beyond Ordinary Lipschitz Constraints: Differentially Private Stochastic Optimization with Tsybakov Noise Condition
by: Xu, Difei, et al.
Published: (2025)

Machine Unlearning via Information Theoretic Regularization
by: Xu, Shizhou, et al.
Published: (2025)

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
by: Zhou, Huichi, et al.
Published: (2025)

Soft Weighted Machine Unlearning
by: Qiao, Xinbao, et al.
Published: (2025)

Towards Safeguarding LLM Fine-tuning APIs against Cipher Attacks
by: Youstra, Jack, et al.
Published: (2025)

LoRA vs Full Fine-tuning: An Illusion of Equivalence
by: Shuttleworth, Reece, et al.
Published: (2024)

Efficient Machine Unlearning via Influence Approximation
by: Liu, Jiawei, et al.
Published: (2025)

A Provably Effective Method for Pruning Experts in Fine-tuned Sparse Mixture-of-Experts
by: Chowdhury, Mohammed Nowaz Rabbani, et al.
Published: (2024)

SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation
by: Ban, Hao, et al.
Published: (2025)

Demystifying Design Choices of Reinforcement Fine-tuning: A Batched Contextual Bandit Learning Perspective
by: Xie, Hong, et al.
Published: (2026)

FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness
by: Wen, Siyuan, et al.
Published: (2025)

Scalable Fine-tuning from Multiple Data Sources: A First-Order Approximation Approach
by: Li, Dongyue, et al.
Published: (2024)

An Information Theoretic Approach to Machine Unlearning
by: Foster, Jack, et al.
Published: (2024)

Towards Revealing the Effectiveness of Small-Scale Fine-tuning in R1-style Reinforcement Learning
by: Chen, Yutong, et al.
Published: (2025)

Auditing Approximate Machine Unlearning for Differentially Private Models
by: Gu, Yuechun, et al.
Published: (2025)

Towards Analyzing and Understanding the Limitations of VAPO: A Theoretical Perspective
by: Shao, Jintian, et al.
Published: (2025)

Understanding Empirical Unlearning with Combinatorial Interpretability
by: Kodama, Shingo, et al.
Published: (2026)

A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts
by: Nakada, Ryumei, et al.
Published: (2025)

Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models
by: Sharma, Aakash Sen, et al.
Published: (2024)