國立虎尾科技大學 |

Beyond Linear Paradigms in Online Control.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Beyond Linear Paradigms in Online Control./
Author:	Minasyan, Edgar.
Description:	1 online resource (260 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
Contained By:	Dissertations Abstracts International85-05B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798380851176

Beyond Linear Paradigms in Online Control.
Minasyan, Edgar.

Beyond Linear Paradigms in Online Control. - 1 online resource (260 pages)

Source: Dissertations Abstracts International, Volume: 85-05, Section: B.

Thesis (Ph.D.)--Princeton University, 2023.

Includes bibliographical references

In the last century, the problem of controlling a dynamical system has been a core component in numerous applications in autonomous systems, engineering, and sciences. The theoretical foundations built so far include the field of classical control theory as well as recent advances in leveraging regret minimization techniques for guarantees in online control. In either case, however, a linearity assumption is prevalent to enable the derivation of provable guarantees and efficient algorithms. In this thesis, we present several directions to alleviate the linearity assumption in the problem of online control. At the core of all the results lies the regret minimization framework: the presented works design new, as well as heavily rely on existing, methods and notions in online convex optimization.The ultimate goal of this direction is to derive efficient algorithms that perform optimal online control of nonlinear dynamical systems. This goal in full generality is NP-hard hence certain concessions need to be made. We build upon the recent non-stochastic control framework that enables efficient online control of linear dynamical systems: our first advance is to consider time-varying linear dynamical systems which are commonly used to approximate nonlinear dynamics. We argue that the correct performance metric in this setting is the notion of adaptive regret developed for online learning in changing environments and proceed to design an efficient control method for known time-varying linear dynamics. The extension to unknown dynamics proves to be qualitatively harder: our upper/lower bound results show that the system variability of the unknown dynamics is a determining factor on whether meaningful (adaptive) regret guarantees can be achieved. The policies in the described advances enjoy linear/convex parameterizations which can be constraining for complex dynamical systems. Hence, we additionally explore the use of neural network-based policies in online episodic control and derive an efficient regret-minimizing algorithm that in-corporates the interpolation dimension as an expressivity metric for the policy class.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380851176Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

NonlinearIndex Terms--Genre/Form:

554714
Electronic books.

Beyond Linear Paradigms in Online Control.
LDR:03461ntm a22003977 4500 001 1151180
005 20241104055820.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380851176
035 $a (MiAaPQ)AAI30691079
035 $a AAI30691079
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Minasyan, Edgar. $3 1477896
245 1 0 $a Beyond Linear Paradigms in Online Control.
264 0 $c 2023
300 $a 1 online resource (260 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
500 $a Advisor: Hazan, Elad.
502 $a Thesis (Ph.D.)--Princeton University, 2023.
504 $a Includes bibliographical references
520 $a In the last century, the problem of controlling a dynamical system has been a core component in numerous applications in autonomous systems, engineering, and sciences. The theoretical foundations built so far include the field of classical control theory as well as recent advances in leveraging regret minimization techniques for guarantees in online control. In either case, however, a linearity assumption is prevalent to enable the derivation of provable guarantees and efficient algorithms. In this thesis, we present several directions to alleviate the linearity assumption in the problem of online control. At the core of all the results lies the regret minimization framework: the presented works design new, as well as heavily rely on existing, methods and notions in online convex optimization.The ultimate goal of this direction is to derive efficient algorithms that perform optimal online control of nonlinear dynamical systems. This goal in full generality is NP-hard hence certain concessions need to be made. We build upon the recent non-stochastic control framework that enables efficient online control of linear dynamical systems: our first advance is to consider time-varying linear dynamical systems which are commonly used to approximate nonlinear dynamics. We argue that the correct performance metric in this setting is the notion of adaptive regret developed for online learning in changing environments and proceed to design an efficient control method for known time-varying linear dynamics. The extension to unknown dynamics proves to be qualitatively harder: our upper/lower bound results show that the system variability of the unknown dynamics is a determining factor on whether meaningful (adaptive) regret guarantees can be achieved. The policies in the described advances enjoy linear/convex parameterizations which can be constraining for complex dynamical systems. Hence, we additionally explore the use of neural network-based policies in online episodic control and derive an efficient regret-minimizing algorithm that in-corporates the interpolation dimension as an expressivity metric for the policy class.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Engineering. $3 561152
650 4 $a Automotive engineering. $3 1104081
653 $a Nonlinear
653 $a Online control
653 $a Online learning
653 $a Regret
653 $a Dynamical system
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0537
690 $a 0540
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Princeton University. $b Computer Science. $3 1179801
773 0 $t Dissertations Abstracts International $g 85-05B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30691079 $z click for full text (PQDT)