1. On the optimization of deep networks: implicit acceleration by overparameterization;Arora,2018
2. Implicit regularization in deep matrix factorization;Arora,2019
3. Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers;Bah;Inf. Inference,2023
4. Neural networks and principal component analysis: learning from examples without local minima;Baldi;Neural Netw.,1989
5. Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks;Bartlett,2018