Imagen de Portada

Sequential Subspace Noise Injection Prevents Accuracy Collapse in Certified Unlearning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dolgova, Polina, Stich, Sebastian U.
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Forgetting Has Neighbors: Localized Collateral Forgetting in Machine Unlearning
por: Dolgova, Polina, et al.
Publicado: (2026)

On the Stability of Nonlinear Dynamics in GD and SGD: Beyond Quadratic Potentials
por: Mulayoff, Rotem, et al.
Publicado: (2026)

Scalable Decentralized Learning with Teleportation
por: Takezawa, Yuki, et al.
Publicado: (2025)

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

Fully Decentralized Certified Unlearning
por: Lamri, Hithem, et al.
Publicado: (2025)

LLM Unlearning using Gradient Ratio-Based Influence Estimation and Noise Injection
por: Anjarlekar, Ameya, et al.
Publicado: (2025)

Locally Adaptive Federated Learning
por: Mukherjee, Sohom, et al.
Publicado: (2023)

Non-convex Stochastic Composite Optimization with Polyak Momentum
por: Gao, Yuan, et al.
Publicado: (2024)

Non-Convex Federated Optimization under Cost-Aware Client Selection
por: Jiang, Xiaowen, et al.
Publicado: (2025)

Federated Optimization with Doubly Regularized Drift Correction
por: Jiang, Xiaowen, et al.
Publicado: (2024)

Stabilized Proximal-Point Methods for Federated Optimization
por: Jiang, Xiaowen, et al.
Publicado: (2024)

Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
por: He, Junlin, et al.
Publicado: (2024)

Certified Unlearning in Decentralized Federated Learning
por: Wu, Hengliang, et al.
Publicado: (2026)

Certified Signed Graph Unlearning
por: Zhao, Junpeng, et al.
Publicado: (2025)

Certified Unlearning for Neural Networks
por: Koloskova, Anastasia, et al.
Publicado: (2025)

Learning When to Adapt
por: Zindari, Ali, et al.
Publicado: (2026)

Towards Faster Decentralized Stochastic Optimization with Communication Compression
por: Islamov, Rustem, et al.
Publicado: (2024)

Towards Certified Unlearning for Deep Neural Networks
por: Zhang, Binchi, et al.
Publicado: (2024)

Hessian-Free Online Certified Unlearning
por: Qiao, Xinbao, et al.
Publicado: (2024)

Certified Minimax Unlearning with Generalization Rates and Deletion Capacity
por: Liu, Jiaqi, et al.
Publicado: (2023)

Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions
por: Mu, Siqiao, et al.
Publicado: (2024)

Accelerated Distributed Optimization with Compression and Error Feedback
por: Gao, Yuan, et al.
Publicado: (2025)

FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
por: Takezawa, Yuki, et al.
Publicado: (2025)

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
por: Zhang, Siqi, et al.
Publicado: (2023)

On Convergence of Incremental Gradient for Non-Convex Smooth Functions
por: Koloskova, Anastasia, et al.
Publicado: (2023)

Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
por: Takezawa, Yuki, et al.
Publicado: (2025)

Decoupled SGDA for Games with Intermittent Strategy Communication
por: Zindari, Ali, et al.
Publicado: (2025)

Scalable and Certifiable Graph Unlearning: Overcoming the Approximation Error Barrier
por: Yi, Lu, et al.
Publicado: (2024)

Machine Unlearning in Low-Dimensional Feature Subspace
por: Fang, Kun, et al.
Publicado: (2026)

ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
por: Wang, Hui-Po, et al.
Publicado: (2021)

Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
por: Esfandiari, Yasin, et al.
Publicado: (2025)

Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach
por: Pandey, Aaradhya, et al.
Publicado: (2025)

IDEA: A Flexible Framework of Certified Unlearning for Graph Neural Networks
por: Dong, Yushun, et al.
Publicado: (2024)

A Certified Unlearning Approach without Access to Source Data
por: Basaran, Umit Yigit, et al.
Publicado: (2025)

Certified Machine Unlearning via Noisy Stochastic Gradient Descent
por: Chien, Eli, et al.
Publicado: (2024)

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization
por: Fraboni, Yann, et al.
Publicado: (2022)

Collective Certified Robustness against Graph Injection Attacks
por: Lai, Yuni, et al.
Publicado: (2024)

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
por: Luo, Ruichen, et al.
Publicado: (2025)

Explaining and Preventing Alignment Collapse in Iterative RLHF
por: Gauthier, Etienne, et al.
Publicado: (2026)

Golden Ratio Weighting Prevents Model Collapse
por: He, Hengzhi, et al.
Publicado: (2025)