Previous research observed accuracy degradation when replacing the atten...
The time-series anomaly detection is one of the most fundamental tasks f...
Anomaly detection is an important field that aims to identify unexpected...
Neural kernels have drastically increased performance on diverse and
non...
Forecasting future outcomes from recent time series data is not easy,
es...
Infinite width limit has shed light on generalization and optimization
a...
The problem of processing very long time-series data (e.g., a length of ...
Deep learning inspired by differential equations is a recent research tr...
Tabular data synthesis has received wide attention in the literature. Th...
The effectiveness of machine learning algorithms arises from being able ...
Synthesizing tabular data is attracting much attention these days for va...
The test loss of well-trained neural networks often follows precise powe...
The predictions of wide Bayesian neural networks are described by a Gaus...
One of the most fundamental aspects of any machine learning algorithm is...
Modern deep learning models have achieved great success in predictive
ac...
We perform a careful, thorough, and large scale empirical study of the
c...
In general, sufficient data is essential for the better performance and
...
This paper reviews the NTIRE 2020 challenge on video quality mapping (VQ...
There are currently two parameterizations used to derive fixed kernels
c...
Neural Tangents is a library designed to enable research into infinite-w...
Selecting an optimizer is a central step in the contemporary deep learni...
We propose that intelligently combining models from the domains of Artif...
A longstanding goal in deep learning research has been to precisely
char...
Recent hardware developments have made unprecedented amounts of data
par...
There is a previously identified equivalence between wide fully connecte...
A deep fully-connected neural network with an i.i.d. prior over its
para...