In this work, we analyze the relation between reparametrizations of grad...
This work bridges two important concepts: the Neural Tangent Kernel (NTK...
Overparameterized models may have many interpolating solutions; implicit...
In many applications, solutions of numerical problems are required to be...
In deep learning it is common to overparameterize the neural networks, t...
We provide an explicit analysis of the dynamics of vanilla gradient desc...
We provide a rigorous analysis of how implicit bias towards smooth
inter...