We study the control of a linear dynamical system with adversarial
disturbances (as opposed to statistical noise). The objective we consider is
one of regret: we desire an online control procedure that can do nearly as well
as that of a procedure that has full knowledge of the disturbances in
hindsight. Our main result is an efficient algorithm that provides nearly tight
regret bounds for this problem. From a technical standpoint, this work
generalizes upon previous work in two main aspects: our model allows for
adversarial noise in the dynamics, and allows for general convex costs.
Description
[1902.08721] Online Control with Adversarial Disturbances
%0 Journal Article
%1 agarwal2019online
%A Agarwal, Naman
%A Bullins, Brian
%A Hazan, Elad
%A Kakade, Sham M.
%A Singh, Karan
%D 2019
%K adversarial optimization robustness
%T Online Control with Adversarial Disturbances
%U http://arxiv.org/abs/1902.08721
%X We study the control of a linear dynamical system with adversarial
disturbances (as opposed to statistical noise). The objective we consider is
one of regret: we desire an online control procedure that can do nearly as well
as that of a procedure that has full knowledge of the disturbances in
hindsight. Our main result is an efficient algorithm that provides nearly tight
regret bounds for this problem. From a technical standpoint, this work
generalizes upon previous work in two main aspects: our model allows for
adversarial noise in the dynamics, and allows for general convex costs.
@article{agarwal2019online,
abstract = {We study the control of a linear dynamical system with adversarial
disturbances (as opposed to statistical noise). The objective we consider is
one of regret: we desire an online control procedure that can do nearly as well
as that of a procedure that has full knowledge of the disturbances in
hindsight. Our main result is an efficient algorithm that provides nearly tight
regret bounds for this problem. From a technical standpoint, this work
generalizes upon previous work in two main aspects: our model allows for
adversarial noise in the dynamics, and allows for general convex costs.},
added-at = {2019-11-04T11:37:08.000+0100},
author = {Agarwal, Naman and Bullins, Brian and Hazan, Elad and Kakade, Sham M. and Singh, Karan},
biburl = {https://www.bibsonomy.org/bibtex/27cde84c259a97359a1eb9c093c9ace6a/kirk86},
description = {[1902.08721] Online Control with Adversarial Disturbances},
interhash = {892697280f893ad966effa69301c29c5},
intrahash = {7cde84c259a97359a1eb9c093c9ace6a},
keywords = {adversarial optimization robustness},
note = {cite arxiv:1902.08721},
timestamp = {2019-11-04T11:37:08.000+0100},
title = {Online Control with Adversarial Disturbances},
url = {http://arxiv.org/abs/1902.08721},
year = 2019
}