Existing theories on deep nonparametric regression have shown that when ...
We propose an effective and robust algorithm for identifying partial
dif...
Autoencoders have demonstrated remarkable success in learning low-dimens...
Generative networks have experienced great empirical successes in
distri...
Label Shift has been widely believed to be harmful to the generalization...
Data-driven identification of differential equations is an interesting b...
Aggregation equations are broadly used to model population dynamics with...
Two-sample tests are important areas aiming to determine whether two
col...
Learning operators between infinitely dimensional spaces is an important...
Most of existing statistical theories on deep neural networks have sampl...
This paper studies the spectral estimation problem of estimating the
loc...
We consider the regression problem of estimating functions on ℝ^D
but su...
Causal inference explores the causation between actions and the conseque...
We propose robust methods to identify underlying Partial Differential
Eq...
Generative Adversarial Networks (GANs) have achieved great success in
un...
Exponential functions are powerful tools to model signals in various
sce...
Many functions of interest are in a high-dimensional space but exhibit
l...
Deep neural networks have revolutionized many real world applications, d...
The problem of imaging point objects can be formulated as estimation of ...
This paper studies stable recovery of a collection of point sources from...
We consider the problem of efficiently approximating and encoding
high-d...