5 papers
Domain Randomization is Sample Efficient for Linear Quadratic Control
Tesshu Fujinami, Bruce D. Lee, Nikolai Matni +1
We study the sample efficiency of domain randomization and robust control for the benchmark problem of learning the linear quadratic regulator (LQR). Domain randomization, which sy…
On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning
Thomas T. Zhang, Behrad Moniri, Ansh Nagwekar +4
Layer-wise preconditioning methods are a family of memory-efficient optimization algorithms that introduce preconditioners per axis of each layer's weight tensors. These methods ha…
State space models, emergence, and ergodicity: How many parameters are needed for stable predictions?
Ingvar Ziemann, Nikolai Matni, George J. Pappas
How many parameters are required for a model to execute a given task? It has been argued that large language models, pre-trained via self-supervised learning, exhibit emergent capa…
Reactive Temporal Logic-based Planning and Control for Interactive Robotic Tasks
Farhad Nawaz, Shaoting Peng, Lars Lindemann +2
Robots interacting with humans must be safe, reactive and adapt online to unforeseen environmental and task changes. Achieving these requirements concurrently is a challenge as int…
Explicit Distributed and Localized Model Predictive Control via System Level Synthesis
Carmen Amo Alonso, Nikolai Matni, James Anderson
An explicit Model Predictive Control algorithm for large-scale structured linear systems is presented. We base our results on Distributed and Localized Model Predictive Control (DL…