東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Beyond Linear Paradigms in Online Co...

Minasyan, Edgar.

FindBook

Google Book

Amazon

博客來

Beyond Linear Paradigms in Online Control.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Beyond Linear Paradigms in Online Control./
作者:	Minasyan, Edgar.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	260 p.
附註:	Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
Contained By:	Dissertations Abstracts International85-05B.
標題:	Computer science. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30691079
ISBN:	9798380851176

Beyond Linear Paradigms in Online Control.
Minasyan, Edgar.

Beyond Linear Paradigms in Online Control. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 260 p.

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

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

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.

ISBN: 9798380851176Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

Nonlinear

Beyond Linear Paradigms in Online Control.
LDR:03261nmm a2200397 4500 001 2402926
005 20241104055820.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380851176
035 $a (MiAaPQ)AAI30691079
035 $a AAI30691079
035 $a 2402926
040 $a MiAaPQ $c MiAaPQ
100 1 $a Minasyan, Edgar. $3 3773186
245 1 0 $a Beyond Linear Paradigms in Online Control.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 260 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-05, Section: B.
500 $a Advisor: Hazan, Elad.
502 $a Thesis (Ph.D.)--Princeton University, 2023.
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.
590 $a School code: 0181.
650 4 $a Computer science. $3 523869
650 4 $a Engineering. $3 586835
650 4 $a Automotive engineering. $3 2181195
653 $a Nonlinear
653 $a Online control
653 $a Online learning
653 $a Regret
653 $a Dynamical system
690 $a 0984
690 $a 0537
690 $a 0540
710 2 $a Princeton University. $b Computer Science. $3 2099280
773 0 $t Dissertations Abstracts International $g 85-05B.
790 $a 0181
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30691079