Image de couverture de livre

How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Alon, Gal, Dar, Yehuda
Format:	Preprint
Publié:	2025
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

How Do the Architecture and Optimizer Affect Representation Learning? On the Training Dynamics of Representations in Deep Neural Networks
par: Sharon, Yuval, et autres
Publié: (2024)

How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation
par: Abitbul, Koren, et autres
Publié: (2023)

Transfer Learning of Linear Regression with Multiple Pretrained Models: Benefiting from More Pretrained Models via Overparameterization Debiasing
par: Boharon, Daniel, et autres
Publié: (2026)

How Does Overparameterization Affect Features?
par: Duzgun, Ahmet Cagri, et autres
Publié: (2024)

Machine Unlearning under Overparameterization
par: Block, Jacob L., et autres
Publié: (2025)

Mixture of Many Zero-Compute Experts: A High-Rate Quantization Theory Perspective
par: Dar, Yehuda
Publié: (2025)

TL-PCA: Transfer Learning of Principal Component Analysis
par: Hendy, Sharon, et autres
Publié: (2024)

Local Linear Recovery Guarantee of Deep Neural Networks at Overparameterization
par: Zhang, Yaoyu, et autres
Publié: (2024)

Double Descent and Other Interpolation Phenomena in GANs
par: Luzi, Lorenzo, et autres
Publié: (2021)

Implicit Regularization and Generalization in Overparameterized Neural Networks
par: Johannsen, Zeran
Publié: (2026)

Regularized Gauss-Newton for Optimizing Overparameterized Neural Networks
par: Adeoye, Adeyemi D., et autres
Publié: (2024)

Towards Certified Unlearning for Deep Neural Networks
par: Zhang, Binchi, et autres
Publié: (2024)

Convergence Analysis of Newton's Method for Neural Networks in the Overparameterized Limit
par: Riedl, Konstantin, et autres
Publié: (2026)

The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression
par: Dar, Yehuda, et autres
Publié: (2021)

How Does Preconditioning Guide Feature Learning in Deep Neural Networks?
par: Yoshida, Kotaro, et autres
Publié: (2025)

Bias of Stochastic Gradient Descent or the Architecture: Disentangling the Effects of Overparameterization of Neural Networks
par: Peleg, Amit, et autres
Publié: (2024)

Provable Generalization in Overparameterized Neural Nets
par: Dhingra, Aviral
Publié: (2025)

Provable Unlearning with Gradient Ascent on Two-Layer ReLU Neural Networks
par: Melamed, Odelia, et autres
Publié: (2025)

Protecting the Neural Networks against FGSM Attack Using Machine Unlearning
par: Khorasani, Amir Hossein, et autres
Publié: (2025)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
par: Cadet, Xavier F., et autres
Publié: (2024)

The Role of Symmetry in Optimizing Overparameterized Networks
par: Sareen, Kusha, et autres
Publié: (2026)

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
par: Zhang, Leyang, et autres
Publié: (2023)

Machine Unlearning using Forgetting Neural Networks
par: Hatua, Amartya, et autres
Publié: (2024)

How Does Quantization Affect Multilingual LLMs?
par: Marchisio, Kelly, et autres
Publié: (2024)

Does Machine Unlearning Truly Remove Knowledge?
par: Chen, Haokun, et autres
Publié: (2025)

Entropic Confinement and Mode Connectivity in Overparameterized Neural Networks
par: Di Carlo, Luca, et autres
Publié: (2025)

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
par: Lai, Kuo-Wei, et autres
Publié: (2026)

ReVeil: Unconstrained Concealed Backdoor Attack on Deep Neural Networks using Machine Unlearning
par: Alam, Manaar, et autres
Publié: (2025)

Towards Initialization-dependent and Non-vacuous Generalization Bounds for Overparameterized Shallow Neural Networks
par: Lei, Yunwen, et autres
Publié: (2026)

Revisiting Optimism and Model Complexity in the Wake of Overparameterized Machine Learning
par: Patil, Pratik, et autres
Publié: (2024)

On the Convergence of Overparameterized Problems: Inherent Properties of the Compositional Structure of Neural Networks
par: de Oliveira, Arthur Castello Branco, et autres
Publié: (2025)

Efficient Compression of Overparameterized Deep Models through Low-Dimensional Learning Dynamics
par: Kwon, Soo Min, et autres
Publié: (2023)

Certified Unlearning for Neural Networks
par: Koloskova, Anastasia, et autres
Publié: (2025)

Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels
par: Tong, Yujia, et autres
Publié: (2025)

More is Better in Modern Machine Learning: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
par: Simon, James B., et autres
Publié: (2023)

The Interpolating Information Criterion for Overparameterized Models
par: Hodgkinson, Liam, et autres
Publié: (2023)

Theoretical Limitations of Ensembles in the Age of Overparameterization
par: Dern, Niclas, et autres
Publié: (2024)

Beyond ReLU: How Activations Affect Neural Kernels and Random Wide Networks
par: Holzmüller, David, et autres
Publié: (2025)

Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?
par: Ba, Yang, et autres
Publié: (2024)

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
par: Gronich, Eitan, et autres
Publié: (2026)