Page 1 of 1

Control & SystemsTheory Seminar at theTechnion

סמסטר חורף, י״ז באדר א׳, תשפ״ד (26 בפברואר 2024)

Title: Robust Learning for Dynamics, Control, and Optimization

Speaker: Prof. Ian R. Manchester, University of Sydney, Australia

Time: Monday, February 26, 2024, 11:30 am (GMT+2)

Place: Room 211, Lady Davis Bldg., Technion – IIT; Zoom ID: 7050439546

Abstract: In this talk, we will introduce a new approach to building neural networks models, both

static (feedforward) and dynamic (recurrent), with built-in guarantees of stability, robust- ness, invertibility and other desirable properties. We will trace the connections between

convex parameterizations from robust control to so-called direct parameterizations, i.e.

smooth & unconstrained parameterisations of all models that satisfy prescribed conditions.

These direct parameterizations enable learning of robust static and dynamic models via sim- ple first-order methods, without any auxiliary constraints or projections. We will explore

some applications in certifiably-robust image classification, physics-informed learning of

contracting nonlinear observers, learning-based control, and learning of "easy-to-optimize"

surrogate loss functions.

Bio: Ian R. Manchester received the B.E. (Hons 1) and Ph.D. degrees in electrical engineering

from the University of New South Wales, Sydney, NSW, Australia, in 2002 and 2006, re- spectively. From 2006-2009 he was a post-doctoral researcher at Umea University, Sweden,

and from 2009-2012 he was a Research scientist at the Massachusetts Institute of Technol- ogy. Since 2012 he has been a faculty member at the University of Sydney, Australia, where

he is currently Professor of Mechatronic Engineering, Director of the Australian Centre for

Robotics, and Director of the Australian Robotic Inspection & Asset Management Hub.

His current research focuses on algorithms for control, estimation, and learning of nonlin- ear dynamical systems, with applications in robotics, robust machine learning, and other

fields.