arXiv Analytics

Sign in

arXiv:2009.13500 [stat.ML]AbstractReferencesReviewsResources

A priori estimates for classification problems using neural networks

Weinan E, Stephan Wojtowytsch

Published 2020-09-28Version 1

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.

Categories: stat.ML, cs.LG, cs.NA, math.NA
Subjects: 68T07, 60-08
Related articles: Most relevant | Search more
arXiv:2006.16941 [stat.ML] (Published 2020-06-30)
Conformal Prediction Intervals for Neural Networks Using Cross Validation
arXiv:2309.09171 [stat.ML] (Published 2023-09-17)
On the Connection Between Riemann Hypothesis and a Special Class of Neural Networks
arXiv:2205.08609 [stat.ML] (Published 2022-05-17)
Bagged Polynomial Regression and Neural Networks

Links

Toolbox