v1v2 (latest)

The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression

13 January 2022

Hamed Hassani

Adel Javanmard

AAML

ArXiv (abs)PDF HTML Github

Papers citing "The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression"

34 / 34 papers shown

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization

199

23 Oct 2025

One-Bit Quantization for Random Features Models

D. Akhtiamov

Reza Ghane

B. Hassibi

192

17 Oct 2025

A Law of Data Reconstruction for Random Features (and Beyond)

195

26 Sep 2025

Asymptotic Analysis of Two-Layer Neural Networks after One Gradient Step under Gaussian Mixtures Data with StructureInternational Conference on Learning Representations (ICLR), 2025

Samet Demir

Zafer Dogan

MLT

368

02 Mar 2025

Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization

Simone Bombari

Marco Mondelli

827

03 Feb 2025

Robust Feature Learning for Multi-Index Models in High DimensionsInternational Conference on Learning Representations (ICLR), 2024

Alireza Mousavi-Hosseini

Adel Javanmard

Murat A. Erdogdu

OOD AAML

563

21 Oct 2024

Feature compression is the root cause of adversarial fragility in neural network classifiers

327

23 Jun 2024

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

...

Battista Biggio

409

14 Jun 2024

H

-Consistency Guarantees for Regression

Anqi Mao

M. Mohri

Yutao Zhong

436

28 Mar 2024

$Asymptotic Behavior of Adversarial Training Estimator under $\ell_\infty$-Perturbation$

Asymptotic Behavior of Adversarial Training Estimator under

\ell_\infty

-Perturbation

Yiling Xie

Xiaoming Huo

327

27 Jan 2024

Learning from Aggregate responses: Instance Level versus Bag Level Loss FunctionsInternational Conference on Learning Representations (ICLR), 2024

Adel Javanmard

Lin Chen

Vahab Mirrokni

Ashwinkumar Badanidiyuru

Gang Fu

248

20 Jan 2024

The Surprising Harmfulness of Benign Overfitting for Adversarial Robustness

Yifan Hao

Tong Zhang

AAML

634

19 Jan 2024

Understanding the Role of Optimization in Double Descent

Chris Yuhao Liu

Jeffrey Flanigan

308

06 Dec 2023

Regularization properties of adversarially-trained linear regressionNeural Information Processing Systems (NeurIPS), 2023

313

16 Oct 2023

A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural NetworksInternational Conference on Machine Learning (ICML), 2023

589

11 Oct 2023

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK ApproachIEEE Transactions on Information Theory (IEEE Trans. Inf. Theory), 2023

Shaopeng Fu

Haiyan Zhao

AAML

442

09 Oct 2023

Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model GeneralizationNeural Information Processing Systems (NeurIPS), 2023

Adel Javanmard

Vahab Mirrokni

484

06 Oct 2023

Universality of max-margin classifiers

283

29 Sep 2023

Robust Linear Regression: Phase-Transitions and Precise Tradeoffs for General Norms

Elvis Dohmatob

M. Scetbon

AAML OOD

233

01 Aug 2023

Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Training

Masaaki Imaizumi

AAML

314

08 Jul 2023

On Achieving Optimal Adversarial Test ErrorInternational Conference on Learning Representations (ICLR), 2023

Justin D. Li

Matus Telgarsky

AAML

306

13 Jun 2023

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent KernelsInternational Conference on Machine Learning (ICML), 2023

512

03 Feb 2023

Robust Linear Regression: Gradient-descent, Early-stopping, and BeyondInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2023

M. Scetbon

Elvis Dohmatob

AAML

259

31 Jan 2023

Demystifying Disagreement-on-the-Line in High DimensionsInternational Conference on Machine Learning (ICML), 2023

392

31 Jan 2023

Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)Neural Information Processing Systems (NeurIPS), 2022

411

15 Sep 2022

Fast Neural Kernel Embeddings for General ActivationsNeural Information Processing Systems (NeurIPS), 2022

327

09 Sep 2022

Rethinking Cost-sensitive Classification in Deep Learning via Adversarial Data AugmentationINFORMS Journal on Data Science (JIDS), 2022

277

24 Aug 2022

Optimal Activation Functions for the Random Features Regression ModelInternational Conference on Learning Representations (ICLR), 2022

Jianxin Wang

José Bento

333

31 May 2022

Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive PowerNeural Information Processing Systems (NeurIPS), 2022

342

27 May 2022

Surprises in adversarially-trained linear regression

495

25 May 2022

Overparameterized Linear Regression under Adversarial AttacksIEEE Transactions on Signal Processing (IEEE Trans. Signal Process.), 2022

Antônio H. Ribeiro

Thomas B. Schon

AAML

231

13 Apr 2022

On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes

Elvis Dohmatob

A. Bietti

AAML

425

22 Mar 2022

Overparametrization improves robustness against adversarial attacks: A replication study

Ali Borji

AAML

203

20 Feb 2022

Precise Statistical Analysis of Classification Accuracies for Adversarial Training

Adel Javanmard

Mahdi Soltanolkotabi

AAML

469

21 Oct 2020