We propose a new bound for generalization of neural networks using Koopm...
This work present novel method for structure estimation of an underlying...
We investigate the approximation property of group convolutional neural
...
Invertible neural networks (INNs) are neural network architectures with
...
Neural network on Riemannian symmetric space such as hyperbolic space an...
Most modern reinforcement learning algorithms optimize a cumulative
sing...
Overparametrization has been remarkably successful for deep learning stu...
Kernel methods have been among the most popular techniques in machine
le...
Neural ordinary differential equations (NODEs) is an invertible neural
n...
In the present study, we investigate a universality of neural networks, ...
Kernel mean embedding (KME) is a powerful tool to analyze probability
me...
Deep learning achieves a high generalization performance in practice, de...
Invertible neural networks based on coupling flows (CF-INNs) have variou...
Kernel methods have been among the most popular techniques in machine
le...
Composition operators have been extensively studied in complex analysis,...
The development of a metric on structural data-generating mechanisms is
...
The development of a metric for structural data is a long-term problem i...
We have obtained an integral representation of the shallow neural networ...