New papers from Control Group members to appear at Control and Learning Conferences this summer

Recent works from the Control group have been accepted and will be presented over the summer at the American Control Conference, the Conference on Learning for Dynamics and Control, and the European Control Conference. The papers cover some of the breadth of topics studied in the Control group, including data-driven optimization and control, neural network verification, distributed learning, and optimal control.

Covid-19 may have an impact as it is uncertain whether the conferences will happen in person, but the respective group members look forward to disseminating the recent research efforts!

Title:  Multi-objective minimum time optimal control for low-thrust trajectory design

Authors: N. Vertovec, S. Ober-Blobaum, and K. Margellos

Conference: European Control Conference (ECC)

Topic: Optimal control

Title:  Tight sampling and discarding bounds for scenario programs with an arbitrary number of removed  samples

Authors: L. Romao, K. Margellos, and A. Papachristodoulou

Conference: Learning for Dynamics and Control (L4DC)

Topic: Data driven optimization

Title:  The optimal transport paradigm enables data compression in data-driven robust control

Authors: F. Fabiani and P. J. Goulart

Conference: American Control Conference (ACC)

Topic: Data driven control

Title:  Robust error bounds for quantised and pruned neural networks

Authors: Jiaqi Li, Ross Drummond and Stephen Duncan

Conference: Learning for Dynamics and Control (L4DC)

Topic: Neural network robustness

Title:  Exploiting Sparsity for Neural Network Verification

Authors: Matthew Newton and Antonis Papachristodoulou  

Conference: Learning for Dynamics and Control (L4DC)

Topic: Neural network robustness

Title:  Linear Regression over Networks with Communication Guarantees

Authors: K Gatsis

Conference: Learning for Dynamics and Control (L4DC)

Topic: Distributed Learning

Title: Adaptive Scheduling for Machine Learning Tasks over Networks

Authors: K Gatsis

Conference: American Control Conference (ACC)

Topic: Distributed Learning