Score: 0

Architecture independent generalization bounds for overparametrized deep ReLU networks

Published: April 8, 2025 | arXiv ID: 2504.05695v3

By: Thomas Chen , Chun-Kai Kevin Chien , Patricia Muñoz Ewald and more

Potential Business Impact:

Makes smart computer programs learn better, no matter how big.

Business Areas:
A/B Testing Data and Analytics

We prove that overparametrized neural networks are able to generalize with a test error that is independent of the level of overparametrization, and independent of the Vapnik-Chervonenkis (VC) dimension. We prove explicit bounds that only depend on the metric geometry of the test and training sets, on the regularity properties of the activation function, and on the operator norms of the weights and norms of biases. For overparametrized deep ReLU networks with a training sample size bounded by the input space dimension, we explicitly construct zero loss minimizers without use of gradient descent, and prove that the generalization error is independent of the network architecture.

Page Count
13 pages

Category
Computer Science:
Machine Learning (CS)