Existing works show that although modern neural networks achieve remarka...
For deep linear networks (DLN), various hyperparameters alter the dynami...
We study how permutation symmetries in overparameterized multi-layer neu...
We study the risk (i.e. generalization error) of Kernel Ridge Regression...
Random Feature (RF) models are used as efficient parametric approximatio...
The permutation symmetry of neurons in each layer of a deep neural netwo...