A priori estimates for classification problems using neural networks

Abstract

We consider binary and multi-class classification problems using hypothesis classes of neural networks. For a given hypothesis class, we use Rademacher complexity estimates and direct approximation theorems to obtain a priori error estimates for regularized loss functionals.

References in corpus (4)

• A Priori Estimates of the Population Risk for Two-layer Neural Networks
• Representation formulas and pointwise properties for Barron functions
• On the Banach spaces associated with multi-layer ReLU networks: Function representation, approximation theory and gradient descent dynamics
• Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels

Cited by in corpus (2)

• The Modern Mathematics of Deep Learning
• Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons