In this paper, we present a sharper version of the results in the paper
...
For the past 30 years or so, machine learning has stimulated a great dea...
In many high-impact applications, it is important to ensure the quality ...
Many applications, such as system identification, classification of time...
A recent paper (Neural Networks, 132 (2020), 253-268) introduces a
strai...
This paper introduces kdiff, a novel kernel-based measure for estimating...
We consider a set of points sampled from an unknown probability measure ...
In much of the literature on function approximation by deep networks, th...
An open problem around deep networks is the apparent absence of over-fit...
A main puzzle of deep networks revolves around the absence of overfittin...