The generalization error of max-margin linear classifiers: Benign
overfitting and high dimensional asymptotics in the overparametrized regime

v1v2v3 (latest)

The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime

5 November 2019

Andrea Montanari

ArXiv (abs)PDF HTML

Papers citing "The generalization error of max-margin linear classifiers: Benign overfitting and high dimensional asymptotics in the overparametrized regime"

8 / 8 papers shown

Title
Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification Xiaohan Zhu Nathan Srebro 118 0 0 03 Mar 2025
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization Simone Bombari Marco Mondelli 303 0 0 03 Feb 2025
High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws M. E. Ildiz Halil Alperen Gozeten Ege Onur Taga Marco Mondelli Samet Oymak 135 5 0 24 Oct 2024
Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality Marko Medvedev Gal Vardi Nathan Srebro 99 3 0 05 Sep 2024
Benign overfitting in leaky ReLU networks with moderate input dimension Kedar Karhadkar Erin E. George Michael Murray Guido Montúfar Deanna Needell MLT 78 2 0 11 Mar 2024
Universality of max-margin classifiers Andrea Montanari Feng Ruan Basil Saeed Youngtak Sohn 71 5 0 29 Sep 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro 83 17 0 02 Mar 2023
Exact spectral norm error of sample covariance Q. Han 72 8 0 27 Jul 2022