Beyond the Universal Law of Robustness: Sharper Laws for Random Features
and Neural Tangent Kernels

v1v2 (latest)

Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels

International Conference on Machine Learning (ICML), 2023

3 February 2023

ArXiv (abs)PDF HTML

Papers citing "Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels"

10 / 10 papers shown

Title
A Law of Data Reconstruction for Random Features (and Beyond) Leonardo Iurada Simone Bombari Tatiana Tommasi Marco Mondelli 92 0 0 26 Sep 2025
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization Simone Bombari Marco Mondelli 594 5 0 03 Feb 2025
Infinite Width Limits of Self Supervised Neural NetworksInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 Maximilian Fleissner Gautham Govind Anil Debarghya Ghoshdastidar SSL 1.0K 2 0 17 Nov 2024
Towards Understanding the Word Sensitivity of Attention Layers: A Study via Random FeaturesInternational Conference on Machine Learning (ICML), 2024 Simone Bombari Marco Mondelli 213 6 0 05 Feb 2024
No Free Prune: Information-Theoretic Barriers to Pruning at Initialization Tanishq Kumar Kevin Luo Mark Sellke 200 7 0 02 Feb 2024
1-Lipschitz Neural Networks are more expressive with N-Activations Bernd Prach Christoph H. Lampert AAML FAtt 163 1 0 10 Nov 2023
Upper and lower bounds for the Lipschitz constant of random neural networks Paul Geuchen Dominik Stöger Dominik Stöger Felix Voigtlaender AAML 354 0 0 02 Nov 2023
A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural NetworksInternational Conference on Machine Learning (ICML), 2023 Behrad Moniri Donghwan Lee Hamed Hassani Guang Cheng MLT 327 31 0 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 326 3 0 09 Oct 2023
How Spurious Features Are Memorized: Precise Analysis for Random and NTK FeaturesInternational Conference on Machine Learning (ICML), 2023 Simone Bombari Marco Mondelli AAML 337 9 0 20 May 2023