Dear all,
We invite registrations for an exciting Workshop on Modern Applications of Control Theory and Reinforcement Learning, particularly to complex adaptive systems:
https://www.cwi.nl/en/events/cwi-research-semester-programmes/workshop-on-m…
Applications of control theory and reinforcement learning are increasingly diverse. This workshop aims to foster the transfer of methods of control and RL across upcoming domains, especially complex adaptive systems such as climate-socio-economics, neuroscience, and similar.
Dates: 20-21 May 2025
Venue: CWI (Research Institute for Mathematics and Computer Science), Amsterdam, Netherlands
Registration deadline: 1 May 2025
We have distinguished speakers covering a wide variety of application domains:
Diederik Roijers, VU Brussel, Belgium
Elena Rovenskaya, International Institute for Applied Systems Analysis (IIASA), Austria
Herke van Hoof, University of Amsterdam, Netherlands
Marcel van Gerven, Radboud University Nijmegen, Netherlands
Marta Kwiatkowska, University of Oxford, United Kingdom
Sander Bohté, CWI, University of Amsterdam, Netherlands
Sander Keemink, Radboud University Nijmegen, Netherlands
Timm Faulwasser, University of Stuttgart, Germany
Wolfram Barfuss, University of Bonn, Germany
Please register as soon as possible!
https://www.cwi.nl/en/events/cwi-research-semester-programmes/workshop-on-m…
This workshop is part of a research semester programme on Control Theory and Reinforcement Learning at CWI, Amsterdam, NL, which comprises a Spring School (17-21 March - deadline 10 March), a Workshop on Themes (24-25 March - deadline 1 March), this Workshop on Modern Applications (20-21 May - deadline 1 May), and an upcoming one on Theory (19-20 June). Download and advertise the poster.
Looking forward to seeing you!
On behalf of the organizers.
Dear all,
It is my pleasure to announce the following CWI Machine Learning seminar
Speaker: Martin Larsson (Carnegie Mellon University)
Title: E-variables for hypotheses generated by constraints
Date: Monday 10 March, 10:30
Location: CWI L016
Please find the abstract below.
Hope to see you then.
Best wishes,
Wouter
Details:
https://www.cwi.nl/en/groups/machine-learning/events/machine-learning-semin…
============
*Title:* E-variables for hypotheses generated by constraints
*Abstract: *There is a natural convex duality relationship between a
statistical
hypothesis and its set of e-variables. If the hypothesis is defined
through a collection of linear constraints, often understood as
(generalized) moment restrictions, then one expects that any e-variable
can be expressed in terms of convex combinations of the constraint
functions. In simple situations, such as for finite sample spaces,
results of this kind can be proved by convex duality in Euclidean space.
However, in more general cases the situation is less clear. In this talk
I will show that e-variable representations of the kind described above
hold in arbitrary sample spaces, without any regularity conditions or
other assumptions whatsoever. I will also discuss a number of examples
illustrating how the abstract theory instantiates in concrete cases.