Papers matching “overparameterized neural networks” 10
Not finding it? Sign in to also search OpenAlex live.
-
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers2021 Information and Inference A Journal of the IMA article Computer Science Stochastic Gradient Optimization Techniques Open access
Bubacarr Bah, Holger Rauhut, Ulrich Terstiege, Michael Westdickenberg
29citations
10 results