
Koopman Spectrum Nonlinear Regulator and Provably Efficient Online Learning
Most modern reinforcement learning algorithms optimize a cumulative sing...
read it

Ghosts in Neural Networks: Existence, Structure and Role of InfiniteDimensional Null Space
Overparametrization has been remarkably successful for deep learning stu...
read it

Reproducing kernel Hilbert C*module and kernel mean embeddings
Kernel methods have been among the most popular techniques in machine le...
read it

Universal Approximation Property of Neural Ordinary Differential Equations
Neural ordinary differential equations (NODEs) is an invertible neural n...
read it

A global universality of twolayer neural networks with ReLU activations
In the present study, we investigate a universality of neural networks, ...
read it

Kernel Mean Embeddings of Von NeumannAlgebraValued Measures
Kernel mean embedding (KME) is a powerful tool to analyze probability me...
read it

Gradient Descent Converges to Ridgelet Spectrum
Deep learning achieves a high generalization performance in practice, de...
read it

Couplingbased Invertible Neural Networks Are Universal Diffeomorphism Approximators
Invertible neural networks based on coupling flows (CFINNs) have variou...
read it

Analysis via Orthonormal Systems in Reproducing Kernel Hilbert C^*Modules and Applications
Kernel methods have been among the most popular techniques in machine le...
read it

Composition operators on reproducing kernel Hilbert spaces with analytic positive definite functions
Composition operators have been extensively studied in complex analysis,...
read it

Metric on random dynamical systems with vectorvalued reproducing kernel Hilbert spaces
The development of a metric on structural datagenerating mechanisms is ...
read it

Metric on Nonlinear Dynamical Systems with Koopman Operators
The development of a metric for structural data is a longterm problem i...
read it

Integral representation of the global minimizer
We have obtained an integral representation of the shallow neural networ...
read it
Isao Ishikawa
is this you? claim profile