Finite-sample Analysis of Interpolating Linear Classifiers in the Overparameterized Regime

Abstract

We prove bounds on the population risk of the maximum margin algorithm for two-class linear classification. For linearly separable training data, the maximum margin algorithm has been shown in previous work to be equivalent to a limit of training with logistic loss using gradient descent, as the training error is driven to zero. We analyze this algorithm applied to random data including misclassification noise. Our assumptions on the clean data include the case in which the class-conditional distributions are standard normal distributions. The misclassification noise may be chosen by an adversary, subject to a limit on the fraction of corrupted labels. Our bounds show that, with sufficient over-parameterization, the maximum margin algorithm trained on noisy data can achieve nearly optimal population risk.

Corrected typographical errors from the previous version of this paper

References in corpus (9)

• High-dimensional classification using features annealed independence rules
• Statistical performance of support vector machines
• In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning
• Implicit Regularization in Deep Learning
• Classification vs regression in overparameterized regimes: Does the loss function matter?
• Interpolating Classifiers Make Few Mistakes
• On the Implicit Bias of Initialization Shape: Beyond Infinitesimal Mirror Descent
• Efficient Learning of Linear Separators under Bounded Noise
• On the Error Resistance of Hinge Loss Minimization

Cited by in corpus (2)

• A Precise High-Dimensional Asymptotic Theory for Boosting and Minimum-${\ell }_1$-Norm Interpolated Classifiers
• High-dimensional Asymptotics of Langevin Dynamics in Spiked Matrix Models