13 citations · 30 across the 3 of their papers we have counts for
6 papers
High-Dimensional Distribution Generation Through Deep Neural Networks
Dmytro Perekrestenko, Léandre Eberhard, Helmut Bölcskei
We show that every -dimensional probability distribution of bounded support can be generated through deep ReLU networks out of a -dimensional uniform input distribution. What…
Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
Dmytro Perekrestenko, Stephan Müller, Helmut Bölcskei
We present an explicit deep neural network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional L…
Deep Neural Network Approximation Theory
Dennis Elbrächter, Dmytro Perekrestenko, Philipp Grohs +1
This paper develops fundamental limits of deep neural network learning by characterizing what is possible if no constraints are imposed on the learning algorithm and on the amount…
The universal approximation power of finite-width deep ReLU networks
Dmytro Perekrestenko, Philipp Grohs, Dennis Elbrächter +1
We show that finite-width deep ReLU neural networks yield rate-distortion optimal approximation (Bölcskei et al., 2018) of polynomials, windowed sinusoidal functions, one-dimension…
Convolutional Recurrent Neural Networks for Electrocardiogram Classification
Martin Zihlmann, Dmytro Perekrestenko, Michael Tschannen
We propose two deep neural network architectures for classification of arbitrary-length electrocardiogram (ECG) recordings and evaluate them on the atrial fibrillation (AF) classif…
Faster Coordinate Descent via Adaptive Importance Sampling
Dmytro Perekrestenko, Volkan Cevher, Martin Jaggi
Coordinate descent methods employ random partial updates of decision variables in order to solve huge-scale convex optimization problems. In this work, we introduce new adaptive ru…