3 papers
cs.LG2023
Mildly Overparameterized ReLU Networks Have a Favorable Loss Landscape
Kedar Karhadkar, Michael Murray, Hanna Tseran +1
We study the loss landscape of both shallow and deep, mildly overparameterized ReLU neural networks on a generic finite input dataset for the squared error loss. We show both by co…
stat.ML2023
Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
Hanna Tseran, Guido Montúfar
We study the gradients of a maxout network with respect to inputs and parameters and obtain bounds for the moments depending on the architecture and the parameter distribution. We…
stat.ML2021
On the Expected Complexity of Maxout Networks
Hanna Tseran, Guido Montúfar
Learning with neural networks relies on the complexity of the representable functions, but more importantly, the particular assignment of typical parameters to functions of differe…