國立虎尾科技大學 |

登入

回首頁

Information-Theoretic Limitations of...

ProQuest Information and Learning Co.

Information-Theoretic Limitations of Distributed Information Processing.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Information-Theoretic Limitations of Distributed Information Processing./
作者:	Xu, Aolin.
面頁冊數:	1 online resource (197 pages)
附註:	Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
Contained By:	Dissertation Abstracts International78-10B(E).
標題:	Electrical engineering. -
電子資源:	click for full text (PQDT)
ISBN:	9781369829549

Information-Theoretic Limitations of Distributed Information Processing.
Xu, Aolin.

Information-Theoretic Limitations of Distributed Information Processing. - 1 online resource (197 pages)

Source: Dissertation Abstracts International, Volume: 78-10(E), Section: B.

Thesis (Ph.D.)

Includes bibliographical references

In a generic distributed information processing system, a number of agents connected by communication channels aim to accomplish a task collectively through local communications. The fundamental limits of distributed information processing problems depend not only on the intrinsic difficulty of the task, but also on the communication constraints due to the distributedness. In this thesis, we reveal these dependencies quantitatively under information-theoretic frameworks.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9781369829549Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Information-Theoretic Limitations of Distributed Information Processing.
LDR:02753ntm a2200349Ki 4500 001 911967
005 20180605073451.5
006 m o u
007 cr mn||||a|a||
008 190606s2016 xx obm 000 0 eng d
020 $a 9781369829549
035 $a (MiAaPQ)AAI10609735
035 $a (MiAaPQ)95358
035 $a AAI10609735
040 $a MiAaPQ $b eng $c MiAaPQ
099 $a TUL $f hyy $c available through World Wide Web
100 1 $a Xu, Aolin. $3 1184122
245 1 0 $a Information-Theoretic Limitations of Distributed Information Processing.
264 0 $c 2016
300 $a 1 online resource (197 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: Dissertation Abstracts International, Volume: 78-10(E), Section: B.
500 $a Adviser: Maxim Raginsky.
502 $a Thesis (Ph.D.) $c University of Illinois at Urbana-Champaign $d 2016.
504 $a Includes bibliographical references
520 $a In a generic distributed information processing system, a number of agents connected by communication channels aim to accomplish a task collectively through local communications. The fundamental limits of distributed information processing problems depend not only on the intrinsic difficulty of the task, but also on the communication constraints due to the distributedness. In this thesis, we reveal these dependencies quantitatively under information-theoretic frameworks.
520 $a We consider three typical distributed information processing problems: decentralized parameter estimation, distributed function computation, and statistical learning under adaptive composition. For the first two problems, we derive converse results on the Bayes risk and the computation time, respectively. For the last problem, we first study the relationship between the generalization capability of a learning algorithm and its stability property measured by the mutual information between its input and output, and then derive achievability results on the generalization error of adaptively composed learning algorithms. In all cases, we obtain general results on the fundamental limits with respect to a general model of the problem, so that the results can be applied to various specific scenarios. Our information-theoretic analyses also provide general approaches to inferring global properties of a distributed information processing system from local properties of its components.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of Illinois at Urbana-Champaign. $b Electrical & Computer Eng. $3 1184123
773 0 $t Dissertation Abstracts International $g 78-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10609735 $z click for full text (PQDT)

筆 0 讀者評論

多媒體

評論

新增評論分享你的心得

Export

取書館別