29 citations · 35 across the 4 of their papers we have counts for
4 papers
Closed-loop training of static output feedback neural network controllers for large systems: A distillation case study
E. M. Turan, J. Jäschke
The online implementation of model predictive control for constrained multivariate systems has two main disadvantages: it requires an estimate of the entire model state and an opti…
Learning a convex cost-to-go for single step model predictive control
E. M. Turan, Z. Mdoe, J. Jäschke
For large uncertain systems, solving model predictive control problems online can be computationally taxing. Using a shorter prediction horizon can help, but may lead to poor perfo…
Bounding-Focused Discretization Methods for the Global Optimization of Nonconvex Semi-Infinite Programs
Evren M. Turan, Johannes Jäschke, Rohit Kannan
We use sensitivity analysis to design bounding-focused discretization (cutting-surface) methods for the global optimization of nonconvex semi-infinite programs (SIPs). We begin by…
Multiple shooting for training neural differential equations on time series
Evren Mert Turan, Johannes Jäschke
Neural differential equations have recently emerged as a flexible data-driven/hybrid approach to model time-series data. This work experimentally demonstrates that if the data cont…