We study benign overfitting in two-layer ReLU networks trained using gra...
We study the loss landscape of two-layer mildly overparameterized ReLU n...
Under mild conditions on the network initialization we derive a power se...
The activation function deployed in a deep neural network has great infl...
We introduce a novel class of matrices which are defined by the factoriz...
Robots navigating in human environments should use language to ask for
a...
Deep Convolutional Sparse Coding (D-CSC) is a framework reminiscent of d...