Statistical learning theory for control: A finite-sample perspective

A Tsiamis, I Ziemann, N Matni… - IEEE Control Systems …, 2023‏ - ieeexplore.ieee.org
Learning algorithms have become an integral component to modern engineering solutions.
Examples range from self-driving cars and recommender systems to finance and even …

Transformers as algorithms: Generalization and stability in in-context learning

Y Li, ME Ildiz, D Papailiopoulos… - … conference on machine …, 2023‏ - proceedings.mlr.press
In-context learning (ICL) is a type of prompting where a transformer model operates on a
sequence of (input, output) examples and performs inference on-the-fly. In this work, we …

Finite sample identification of bilinear dynamical systems

Y Sattar, S Oymak, N Ozay - 2022 IEEE 61st Conference on …, 2022‏ - ieeexplore.ieee.org
Bilinear dynamical systems are ubiquitous in many different domains and they can also be
used to approximate more general control-affine systems. This motivates the problem of …

Smoothed online learning for prediction in piecewise affine systems

A Block, M Simchowitz… - Advances in Neural …, 2023‏ - proceedings.neurips.cc
The problem of piecewise affine (PWA) regression and planning is of foundational
importance to the study of online learning, control, and robotics, where it provides a …

Learning linear dynamics from bilinear observations

Y Sattar, Y Jedra, S Dean - arxiv preprint arxiv:2409.16499, 2024‏ - arxiv.org
We consider the problem of learning a realization of a partially observed dynamical system
with linear state transitions and bilinear observations. Under very mild assumptions on the …

Data-driven control of markov jump systems: Sample complexity and regret bounds

Z Du, Y Sattar, DA Tarzanagh, L Balzano… - 2022 American …, 2022‏ - ieeexplore.ieee.org
Learning how to effectively control unknown dynamical systems from data is crucial for
intelligent autonomous systems. This task becomes a significant challenge when the …

Oracle-efficient smoothed online learning for piecewise continuous decision making

A Block, M Simchowitz… - The Thirty Sixth Annual …, 2023‏ - proceedings.mlr.press
Smoothed online learning has emerged as a popular framework to mitigate the substantial
loss in statistical and computational complexity that arises when one moves from classical to …

Optimal competitive-ratio control

O Sabag, S Lale, B Hassibi - arxiv preprint arxiv:2206.01782, 2022‏ - arxiv.org
Inspired by competitive policy designs approaches in online learning, new control
paradigms such as competitive-ratio and regret-optimal control have been recently …

Strong consistency and rate of convergence of switched least squares system identification for autonomous markov jump linear systems

B Sayedana, M Afshari, PE Caines… - IEEE Transactions on …, 2024‏ - ieeexplore.ieee.org
In this article, we investigate the problem of system identification for autonomous Markov
jump linear systems (MJS) with complete state observations. We propose switched least …

Finite-sample analysis of identification of switched linear systems with arbitrary or restricted switching

S Shi, O Mazhar, B De Schutter - IEEE Control Systems Letters, 2022‏ - ieeexplore.ieee.org
For the identification of switched systems with measured states and a measured switching
signal, this letter aims to analyze the effect of switching strategies on the estimation error …