no code implementations • 13 Apr 2024 • Bruce D. Lee, Ingvar Ziemann, George J. Pappas, Nikolai Matni
Model-based reinforcement learning is an effective approach for controlling an unknown system.
no code implementations • 11 Apr 2024 • Charis Stamouli, Ingvar Ziemann, George J. Pappas
We study the quadratic prediction error method -- i. e., nonlinear least squares -- for a class of time-varying parametric predictor models satisfying a certain identifiability condition.
no code implementations • 8 Feb 2024 • Ingvar Ziemann, Stephen Tu, George J. Pappas, Nikolai Matni
We show that whenever the topologies of $L^2$ and $\Psi_p$ are comparable on our hypothesis class $\mathscr{F}$ -- that is, $\mathscr{F}$ is a weakly sub-Gaussian class: $\|f\|_{\Psi_p} \lesssim \|f\|_{L^2}^\eta$ for some $\eta\in (0, 1]$ -- the empirical risk minimizer achieves a rate that only depends on the complexity of the class and second order statistics in its leading term.
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 • 19 Dec 2022 • Ingvar Ziemann
We present a simple proof for bounding the smallest eigenvalue of the empirical covariance in a causal Gaussian process.
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.
1 code implementation • 16 Jun 2022 • Ingvar Ziemann, Stephen Tu
We study square loss in a realizable time-series framework with martingale difference noise.
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 • 16 Feb 2022 • Ingvar Ziemann, Henrik Sandberg, Nikolai Matni
Given a single trajectory of a dynamical system, we analyze the performance of the nonparametric least squares estimator (LSE).
no code implementations • 5 Jan 2022 • Ingvar Ziemann, Henrik Sandberg
TWe establish regret lower bounds for adaptively controlling an unknown linear Gaussian system with quadratic costs.
no code implementations • 18 Nov 2020 • Ingvar Ziemann, Henrik Sandberg
After defining the intrinsic notion of an uninformative optimal policy in terms of a singularity condition for Fisher information we obtain local minimax regret lower bounds for such uninformative instances of LQR by appealing to van Trees' inequality (Bayesian Cram\'er-Rao) and a representation of regret in terms of a quadratic form (Bellman error).