Learning and decision-making with data: Optimal formulations and phase transitions
A Bennouna, BPG Van Parys - arXiv preprint arXiv:2109.06911, 2021 - arxiv.org
We study the problem of designing optimal learning and decision-making formulations when
only historical data is available. Prior work typically commits to a particular class of data …
only historical data is available. Prior work typically commits to a particular class of data …
Efficient learning of a linear dynamical system with stability guarantees
We propose a principled method for projecting an arbitrary square matrix to the nonconvex
set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we …
set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we …
Data-Driven and Stealthy Deactivation of Safety Filters
D Arnström, AMH Teixeira - arXiv preprint arXiv:2412.01346, 2024 - arxiv.org
Safety filters ensure that control actions that are executed are always safe, no matter the
controller in question. Previous work has proposed a simple and stealthy false-data injection …
controller in question. Previous work has proposed a simple and stealthy false-data injection …
On topological equivalence in linear quadratic optimal control
W Jongeneel, D Kuhn - 2021 European Control Conference …, 2021 - ieeexplore.ieee.org
Dynamical systems are topologically equivalent when their orbits can be mapped onto each
other via a homeomorphic change of coordinates. We will show that in general, closed-loop …
other via a homeomorphic change of coordinates. We will show that in general, closed-loop …
Efficient Robustness and Interpretability in Learning and Data-Driven Decision-Making
MA Bennouna - 2024 - dspace.mit.edu
As machine learning algorithms are increasingly developed and deployed in high-stakes
applications, ensuring their reliability has become crucial. This thesis introduces algorithmic …
applications, ensuring their reliability has become crucial. This thesis introduces algorithmic …
Topological Obstructions
W Jongeneel, E Moulay - … Obstructions to Stability and Stabilization: History …, 2023 - Springer
Given the previous chapters on topology and dynamical system theory, we can now provide
a consistent treatment of topological obstructions to stability and stabilization. In particular …
a consistent treatment of topological obstructions to stability and stabilization. In particular …