8 papers
Online Learning for Supervisory Switching Control
Haoyuan Sun, Ali Jadbabaie
We study supervisory switching control for partially-observed linear dynamical systems. The objective is to identify and deploy a suitable controller for the unknown system by peri…
Sparse Representations of Dynamical Networks: A Coprime Factorization Approach
Åerban SabÄu, Andrei SperilÄ, Cristian OarÄ +1
We study a class of dynamical networks modeled by linear and time-invariant systems which are described by state-space realizations. For these networks, we investigate the relation…
On the Role of Transformer Feed-Forward Layers in Nonlinear In-Context Learning
Haoyuan Sun, Ali Jadbabaie, Navid Azizan
Transformer-based models demonstrate a remarkable ability for in-context learning (ICL), where they can adapt to unseen tasks from a few prompt examples without parameter updates.…
Non-submodular Visual Attention for Robot Navigation
Reza Vafaee, Kian Behzad, Milad Siami +2
This paper presents a task-oriented computational framework to enhance Visual-Inertial Navigation (VIN) in robots, addressing challenges such as limited time and energy resources.…
Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
Michael Scholkemper, Xinyi Wu, Ali Jadbabaie +1
Residual connections and normalization layers have become standard design choices for graph neural networks (GNNs), and were proposed as solutions to the mitigate the oversmoothing…
Optimal estimation in spatially distributed systems: how far to share measurements from?
Juncal Arbelaiz, Bassam Bamieh, Anette E. Hosoi +1
We consider the centralized optimal estimation problem in spatially distributed systems. We use the setting of spatially invariant systems as an idealization for which concrete and…