no code implementations • 6 Sep 2024 • Anastasios Vlachos, Anastasios Tsiamis, Aren Karapetyan, Efe C. Balta, John Lygeros

In this paper, we consider the problem of predicting unknown targets from data.

no code implementations • 2 Apr 2024 • Aren Karapetyan, Efe C. Balta, Anastasios Tsiamis, Andrea Iannelli, John Lygeros

Continuous-time adaptive controllers for systems with a matched uncertainty often comprise an online parameter estimator and a corresponding parameterized controller to cancel the uncertainty.

no code implementations • 1 Apr 2024 • Anastasios Tsiamis, Mohamed Abdalmoaty, Roy S. Smith, John Lygeros

The error rate is of the order of $\mathcal{O}((d_{\mathrm{u}}+\sqrt{d_{\mathrm{u}}d_{\mathrm{y}}})\sqrt{M/N_{\mathrm{tot}}})$, where $N_{\mathrm{tot}}$ is the total number of samples, $M$ is the number of desired frequencies, and $d_{\mathrm{u}},\, d_{\mathrm{y}}$ are the dimensions of the input and output signals respectively.

no code implementations • 15 Feb 2024 • Anastasios Tsiamis, Aren Karapetyan, Yueshan Li, Efe C. Balta, John Lygeros

The learned model is used in the optimal policy under the framework of receding horizon control.

no code implementations • 7 Sep 2023 • Ingvar Ziemann, Anastasios Tsiamis, Bruce Lee, Yassir Jedra, Nikolai Matni, George J. Pappas

This tutorial serves as an introduction to recently developed non-asymptotic methods in the theory of -- mainly linear -- system identification.

no code implementations • 27 Mar 2023 • Bruce D. Lee, Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg, Nikolai Matni

We present a local minimax lower bound on the excess cost of designing a linear-quadratic controller from offline data.

no code implementations • 17 Mar 2023 • Aren Karapetyan, Diego Bolliger, Anastasios Tsiamis, Efe C. Balta, John Lygeros

Online learning algorithms for dynamical systems provide finite time guarantees for control in the presence of sequentially revealed cost functions.

no code implementations • 19 Jan 2023 • Shengling Shi, Anastasios Tsiamis, Bart De Schutter

In this work, we aim to analyze how the trade-off between the modeling error, the terminal value function error, and the prediction horizon affects the performance of a nominal receding-horizon linear quadratic (LQ) controller.

no code implementations • 14 Nov 2022 • Aren Karapetyan, Anastasios Tsiamis, Efe C. Balta, Andrea Iannelli, John Lygeros

The setting of an agent making decisions under uncertainty and under dynamic constraints is common for the fields of optimal control, reinforcement learning, and recently also for online learning.

no code implementations • 12 Sep 2022 • Anastasia Impicciatore, Anastasios Tsiamis, Yuriy Zacchia Lun, Alessandro D'Innocenzo, George J. Pappas

This note studies state estimation in wireless networked control systems with secrecy against eavesdropping.

no code implementations • 12 Sep 2022 • Anastasios Tsiamis, Ingvar Ziemann, Nikolai Matni, George J. Pappas

This tutorial survey provides an overview of recent non-asymptotic advances in statistical learning theory as relevant to control and system identification.

no code implementations • 14 Jun 2022 • Ingvar Ziemann, Anastasios Tsiamis, Henrik Sandberg, Nikolai Matni

We study stochastic policy gradient methods from the perspective of control-theoretic limitations.

no code implementations • 27 May 2022 • Anastasios Tsiamis, Ingvar Ziemann, Manfred Morari, Nikolai Matni, George J. Pappas

In this paper, we study the statistical difficulty of learning to control linear systems.

no code implementations • 3 Apr 2022 • Charis Stamouli, Anastasios Tsiamis, Manfred Morari, George J. Pappas

Then, we employ this benchmark controller to derive a novel robustly stable adaptive SMPC scheme that learns the necessary noise statistics online, while guaranteeing time-uniform satisfaction of the unknown reformulated state constraints with high probability.

no code implementations • 2 Apr 2021 • Anastasios Tsiamis, George J. Pappas

Statistically easy to learn linear system classes have sample complexity that is polynomial with the system dimension.

no code implementations • 6 Nov 2020 • Nikos Tsilivis, Anastasios Tsiamis, Petros Maragos

In this work, we study the problem of finding approximate, with minimum support set, solutions to matrix max-plus equations, which we call sparse approximate solutions.

no code implementations • 12 Feb 2020 • Anastasios Tsiamis, George Pappas

When the system model is unknown, we have to learn how to predict observations online based on finite data, suffering possibly a non-zero regret with respect to the Kalman filter's prediction.

no code implementations • L4DC 2020 • Anastasios Tsiamis, Nikolai Matni, George J. Pappas

We show that when the system identification step produces sufficiently accurate estimates, or when the underlying true KF is sufficiently robust, that a Certainty Equivalent (CE) KF, i. e., one designed using the estimated parameters directly, enjoys provable sub-optimality guarantees.

no code implementations • 21 Mar 2019 • Anastasios Tsiamis, George J. Pappas

In this paper, we analyze the finite sample complexity of stochastic system identification using modern tools from machine learning and statistics.

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.