Paper ID: 2405.16958
Large Deviations of Gaussian Neural Networks with ReLU activation
Quirin Vogel
We prove a large deviation principle for deep neural networks with Gaussian weights and (at most linearly growing) activation functions. This generalises earlier work, in which bounded and continuous activation functions were considered. In practice, linearly growing activation functions such as ReLU are most commonly used. We furthermore simplify previous expressions for the rate function and a give power-series expansions for the ReLU case.
Submitted: May 27, 2024