The dynamic Schrödinger bridge problem seeks a stochastic process that
d...
There is a recent literature on large-width properties of Gaussian neura...
In modern deep learning, there is a recent and growing literature on the...
We systematically develop a learning-based treatment of stochastic optim...
In this paper, we consider fully connected feed-forward deep neural netw...
The count-min sketch (CMS) is a time and memory efficient randomized dat...
The count-min sketch (CMS) is a randomized data structure that provides
...
The interplay between infinite-width neural networks (NNs) and classes o...
When neural network's parameters are initialized as i.i.d., neural netwo...
We consider fully connected feed-forward deep neural networks (NNs) wher...
Recent algorithms with state-of-the-art few-shot classification results ...
Deep neural networks whose parameters are distributed according to typic...