activity
20152022
most citedSpline parameterization of neural network controls for deep learning

4 citations · 8 across the 5 of their papers we have counts for

collaborators

7 papers

math.NA20221 cited

Toward Parallel in Time for Chaotic Dynamical Systems

David A. Vargas, Robert D. Falgout, Stefanie Günther +1

As CPU clock speeds have stagnated, and high performance computers continue to have ever higher core counts, increased parallelism is needed to take advantage of these new architec…

quant-ph20212 cited

Quandary: An open-source C++ package for high-performance optimal control of open quantum systems

Stefanie Günther, N. Anders Petersson, Jonathan L. Dubois

Quantum optimal control can be used to shape the control pulses for realizing unitary and non-unitary transformations of quantum states. These control pulses provide the fundamenta…

cs.LG20214 cited

Spline parameterization of neural network controls for deep learning

Stefanie Günther, Will Pazner, Dongping Qi

Based on the continuous interpretation of deep learning cast as an optimal control problem, this paper investigates the benefits of employing B-spline basis functions to parameteri…

cs.LG20191 cited

Multilevel Initialization for Layer-Parallel Deep Neural Network Training

Eric C. Cyr, Stefanie Günther, Jacob B. Schroder

This paper investigates multilevel initialization strategies for training very deep neural networks with a layer-parallel multigrid solver. The scheme is based on the continuous in…

math.OC2018

Layer-Parallel Training of Deep Residual Neural Networks

S. Günther, L. Ruthotto, J. B. Schroder +2

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification an…

math.OC2018

A Non-Intrusive Parallel-in-Time Approach for Simultaneous Optimization with Unsteady PDEs

Stefanie Günther, Nicolas R. Gauger, Jacob B. Schroder

This paper presents a non-intrusive framework for integrating existing unsteady partial differential equation (PDE) solvers into a parallel-in-time simultaneous optimization algori…