Imagen de Portada

Efficient machine unlearning with minimax optimality

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xie, Jingyi, Zhang, Linjun, Li, Sai
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

Personalizing black-box models for nonparametric regression with minimax optimality
por: Li, Sai, et al.
Publicado: (2026)

FAIRM: Learning invariant representations for algorithmic fairness and domain generalization with minimax optimality
por: Li, Sai, et al.
Publicado: (2024)

Scalability of memorization-based machine unlearning
por: Zhao, Kairan, et al.
Publicado: (2024)

A hybrid framework for effective and efficient machine unlearning
por: Li, Mingxin, et al.
Publicado: (2024)

Superior resilience to poisoning and amenability to unlearning in quantum machine learning
por: Chen, Yu-Qin, et al.
Publicado: (2025)

Worst-case generation via minimax optimization in Wasserstein space
por: Cheng, Xiuyuan, et al.
Publicado: (2025)

Flow matching achieves almost minimax optimal convergence
por: Fukumizu, Kenji, et al.
Publicado: (2024)

Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition
por: Triantafillou, Eleni, et al.
Publicado: (2024)

On the limitation of evaluating machine unlearning using only a single training seed
por: Lanyon, Jamie, et al.
Publicado: (2025)

Is your algorithm unlearning or untraining?
por: Triantafillou, Eleni, et al.
Publicado: (2026)

Towards minimax optimal algorithms for Active Simple Hypothesis Testing
por: Vijayan, Sushant
Publicado: (2025)

minimax: Efficient Baselines for Autocurricula in JAX
por: Jiang, Minqi, et al.
Publicado: (2023)

Locally minimax optimal confidence sets for the best model
por: Kim, Ilmun, et al.
Publicado: (2025)

A conversion theorem and minimax optimality for continuum contextual bandits
por: Akhavan, Arya, et al.
Publicado: (2024)

Deep learning from strongly mixing observations: Sparse-penalized regularization and minimax optimality
por: Kengne, William, et al.
Publicado: (2024)

What makes unlearning hard and what to do about it
por: Zhao, Kairan, et al.
Publicado: (2024)

A minimax optimal control approach for robust neural ODEs
por: Cipriani, Cristina, et al.
Publicado: (2023)

Provable unlearning in topic modeling and downstream tasks
por: Wei, Stanley, et al.
Publicado: (2024)

Machine unlearning through fine-grained model parameters perturbation
por: Zuo, Zhiwei, et al.
Publicado: (2024)

Two-Sided Nearest Neighbors: An adaptive and minimax optimal procedure for matrix completion
por: Sadhukhan, Tathagata, et al.
Publicado: (2024)

A mean teacher algorithm for unlearning of language models
por: Klochkov, Yegor
Publicado: (2025)

Applying sparse autoencoders to unlearn knowledge in language models
por: Farrell, Eoin, et al.
Publicado: (2024)

How to unlearn a learned Machine Learning model ?
por: Achour, Seifeddine
Publicado: (2024)

When unlearning is free: leveraging low influence points to reduce computational costs
por: Kleiman, Anat, et al.
Publicado: (2025)

Linear bandits with polylogarithmic minimax regret
por: Lumbreras, Josep, et al.
Publicado: (2024)

FaiREE: Fair Classification with Finite-Sample and Distribution-Free Guarantee
por: Li, Puheng, et al.
Publicado: (2022)

Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening
por: Schoepf, Stefan, et al.
Publicado: (2024)

Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data
por: Schoepf, Stefan, et al.
Publicado: (2025)

Finite-Sample and Distribution-Free Fair Classification: Optimal Trade-off Between Excess Risk and Fairness, and the Cost of Group-Blindness
por: Hou, Xiaotian, et al.
Publicado: (2024)

Solving bilevel optimization via sequential minimax optimization
por: Lu, Zhaosong, et al.
Publicado: (2025)

On the minimax optimality of Flow Matching through the connection to kernel density estimation
por: Kunkel, Lea, et al.
Publicado: (2025)

Cross-Modal Safety Alignment: Is textual unlearning all you need?
por: Chakraborty, Trishna, et al.
Publicado: (2024)

Training data attribution in diffusion models via mirrored unlearning and noise-consistent skew
por: Serrà, Joan, et al.
Publicado: (2026)

Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise
por: Ye, Haotian, et al.
Publicado: (2022)

Synthetic Oversampling: Theory and A Practical Approach Using LLMs to Address Data Imbalance
por: Nakada, Ryumei, et al.
Publicado: (2024)

HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning
por: Wang, Liyuan, et al.
Publicado: (2024)

Exploring bidirectional bounds for minimax-training of Energy-based models
por: Geng, Cong, et al.
Publicado: (2025)

Statistical Inference for Differentially Private Stochastic Gradient Descent
por: Xia, Xintao, et al.
Publicado: (2025)

Regularized least squares learning with heavy-tailed noise is minimax optimal
por: Mollenhauer, Mattes, et al.
Publicado: (2025)

Regret-Based $(ε,δ)$-optimal Stopping Criteria for Bayesian Optimization
por: Wang, Haowei, et al.
Publicado: (2026)