Many supervised learning problems involve high-dimensional data such as
...
This work presents a multilevel variant of Stein variational gradient de...
High-dimensional depth separation results for neural networks show that
...
Classical reduced models are low-rank approximations using a fixed basis...
The remarkable performance of deep neural networks depends on the
availa...
Neural networks provide a rich class of high-dimensional, non-convex
opt...
We investigate a series of learning kernel problems with polynomial
comb...