Many mathematical convergence results for gradient descent (GD) based
al...
In this article we propose a new deep learning approach to solve paramet...
In this article we study high-dimensional approximation capacities of sh...
In this paper we develop a numerical method for efficiently approximatin...
Dynamical systems theory has recently been applied in optimization to pr...
The training of artificial neural networks (ANNs) is nowadays a highly
r...
It is an elementary fact in the scientific literature that the Lipschitz...
Nonlinear partial differential equations (PDEs) are used to model dynami...
In financial engineering, prices of financial products are computed
appr...
The purpose of this article is to develop machinery to study the capacit...
In this article we study fully-connected feedforward deep ReLU ANNs with...
In many numerical simulations stochastic gradient descent (SGD) type
opt...
Full-history recursive multilevel Picard (MLP) approximation schemes hav...
Backward stochastic differential equations (BSDEs) belong nowadays to th...
The training of artificial neural networks (ANNs) with rectified linear ...
Gradient descent (GD) type optimization methods are the standard instrum...
Gradient descent (GD) type optimization schemes are the standard methods...
In this article we study the stochastic gradient descent (SGD) optimizat...
In this paper, we analyze the landscape of the true loss of a ReLU neura...
Artificial neural networks (ANNs) have become a very powerful tool in th...
We consider ordinary differential equations (ODEs) which involve expecta...
In recent years, artificial neural networks have developed into a powerf...
Gradient descent optimization algorithms are the standard ingredients th...
It is one of the most challenging problems in applied mathematics to
app...
Although deep learning based approximation algorithms have been applied ...
In this paper we develop a new machinery to study the capacity of artifi...
In this article we introduce and study a deep learning based approximati...
The approximative calculation of iterated nested expectations is a recur...
The recently introduced full-history recursive multilevel Picard (MLP)
a...
In recent years, tremendous progress has been made on numerical algorith...
Stochastic gradient descent (SGD) type optimization schemes are fundamen...
Deep neural networks have successfully been trained in various applicati...
It is one of the most challenging issues in applied mathematics to
appro...
One of the most challenging issues in applied mathematics is to develop ...
In spite of the accomplishments of deep learning based algorithms in num...
Recently, so-called full-history recursive multilevel Picard (MLP)
appro...
In this paper, we develop an approximation theory for deep neural networ...
Partial differential equations (PDEs) are a fundamental tool in the mode...
Recently, artificial neural networks (ANNs) in conjunction with stochast...
It is one of the most challenging problems in applied mathematics to
app...
The main result of this article establishes strong convergence rates on ...
Deep learning algorithms have been applied very successfully in recent y...
Recently, it has been proposed in the literature to employ deep neural
n...
Over the last few years deep artificial neural networks (DNNs) have very...
Nowadays many financial derivatives which are traded on stock and future...
One of the most challenging problems in applied mathematics is the
appro...
In this paper we introduce a numerical method for parabolic PDEs that
co...
Although for neural networks with locally Lipschitz continuous activatio...
We prove the local convergence to minima and estimates on the rate of
co...
The development of new classification and regression algorithms based on...