We provide a new variational definition for the spread of an orbital und...
We develop an eigenspace estimation algorithm for distributed environmen...
We propose a new technique for constructing low-rank approximations of
m...
We introduce a principled approach to neural network pruning that casts ...
Kernel methods are a highly effective and widely used collection of mode...
Rational approximation schemes for reconstructing signals from samples w...
We draw connections between simple neural networks and under-determined
...
Distributed computing is a standard way to scale up machine learning and...
Matrix square roots and their inverses arise frequently in machine learn...
Several problems in machine learning, statistics, and other fields rely ...
This paper presents a general method for applying hierarchical matrix
sk...
Several fundamental tasks in data science rely on computing an extremal
...
For a fixed matrix A and perturbation E we develop purely deterministic
...