Cover Image

Why Some Models Resist Unlearning: A Linear Stability Perspective

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Wei-Kai, Khanna, Rajiv
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias
by: Chang, Wei-Kai, et al.
Published: (2025)

Sharpness-Aware Machine Unlearning
by: Tang, Haoran, et al.
Published: (2025)

Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
by: Chang, Wei-Kai, et al.
Published: (2025)

From Logits to Latents: Contrastive Representation Shaping for LLM Unlearning
by: Tang, Haoran, et al.
Published: (2026)

A Precise Characterization of SGD Stability Using Loss Surface Geometry
by: Dexter, Gregory, et al.
Published: (2024)

Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective
by: Lee, Justin, et al.
Published: (2025)

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

SAMOSA: Sharpness Aware Minimization for Open Set Active learning
by: Kim, Young In, et al.
Published: (2025)

Escaping the Mode Lottery: Multi-Response Training Improves Language Model Generalization
by: Amin, Hasan, et al.
Published: (2026)

The Space Complexity of Approximating Logistic Loss
by: Dexter, Gregory, et al.
Published: (2024)

Structure-Aware Spectral Sparsification via Uniform Edge Sampling
by: He, Kaiwen, et al.
Published: (2025)

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

BLUR: A Bi-Level Optimization Approach for LLM Unlearning
by: Reisizadeh, Hadi, et al.
Published: (2025)

Align When They Want, Complement When They Need! Human-Centered Ensembles for Adaptive Human-AI Collaboration
by: Amin, Hasan, et al.
Published: (2026)

A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
by: Scholten, Yan, et al.
Published: (2024)

Why Do Some Inputs Break Low-Bit LLM Quantization?
by: Chang, Ting-Yun, et al.
Published: (2025)

Consistent Diffusion Language Models
by: Amin, Hasan, et al.
Published: (2026)

LUME: LLM Unlearning with Multitask Evaluations
by: Ramakrishna, Anil, et al.
Published: (2025)

Instance-Level Difficulty: A Missing Perspective in Machine Unlearning
by: Rizwan, Hammad, et al.
Published: (2024)

Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspective
by: Ding, Meng, et al.
Published: (2024)

Why Do Some Language Models Fake Alignment While Others Don't?
by: Sheshadri, Abhay, et al.
Published: (2025)

Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data
by: Roy, Dip, et al.
Published: (2026)

Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
by: Wang, Qizhou, et al.
Published: (2025)

FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
by: Li, Yue, et al.
Published: (2026)

SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
by: Ramakrishna, Anil, et al.
Published: (2025)

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
by: Bu, Zhiqi, et al.
Published: (2024)

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

Backdoor Unlearning by Linear Task Decomposition
by: Abdelraheem, Amel, et al.
Published: (2025)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
by: Mushtaq, Erum, et al.
Published: (2025)

How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
by: Qiu, Xinchi, et al.
Published: (2024)

SoK: A Review of Differentially Private Linear Models For High-Dimensional Data
by: Khanna, Amol, et al.
Published: (2024)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models
by: Tang, Haoyu, et al.
Published: (2024)

Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective
by: Panda, Subhodip, et al.
Published: (2024)

Data Unlearning in Diffusion Models
by: Alberti, Silas, et al.
Published: (2025)

Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
by: Chen, Yiwei, et al.
Published: (2025)

Membership Privacy Risks of Sharpness Aware Minimization
by: Kim, Young In, et al.
Published: (2023)

The Stability of Singular Distribution: A Spectral Perspective on the Two-Phase Dynamics of Language Model Pre-training
by: Zhang, Hongtao, et al.
Published: (2026)

Beyond Uniform Deletion: A Data Value-Weighted Framework for Certified Machine Unlearning
by: He, Lisong, et al.
Published: (2025)

Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors
by: Alkhatib, Yahya, et al.
Published: (2025)