國立虎尾科技大學 |

Reliable Online Prediction with Refuse Option.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Reliable Online Prediction with Refuse Option./
作者:	Kocak, Mustafa Anil.
面頁冊數:	1 online resource (102 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Artificial intelligence. -
電子資源:	click for full text (PQDT)
ISBN:	9780355981407

Reliable Online Prediction with Refuse Option.
Kocak, Mustafa Anil.

Reliable Online Prediction with Refuse Option. - 1 online resource (102 pages)

Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.

Thesis (Ph.D.)--New York University Tandon School of Engineering, 2018.

Includes bibliographical references

Prediction of the upcoming points in a data stream, online prediction , is a fundamental problem in machine learning. In this thesis, we design meta-algorithms that can take any standard online prediction algorithm and provably improve its performance, given the right to refuse to make predictions in some instances. Allowing refusals means that the meta-algorithm may decline to emit a prediction produced by the base algorithm on occasion. We investigate this problem in two different settings.

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

Mode of access: World Wide Web

ISBN: 9780355981407Subjects--Topical Terms:

559380
Artificial intelligence.
Index Terms--Genre/Form:

554714
Electronic books.

Reliable Online Prediction with Refuse Option.
LDR:03468ntm a2200361Ki 4500 001 916829
005 20180928111501.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780355981407
035 $a (MiAaPQ)AAI10641615
035 $a (MiAaPQ)poly:10373
035 $a AAI10641615
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kocak, Mustafa Anil. $3 1190678
245 1 0 $a Reliable Online Prediction with Refuse Option.
264 0 $c 2018
300 $a 1 online resource (102 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: 79-10(E), Section: B.
500 $a Advisers: Elza Erkip; Dennis E. Shasha.
502 $a Thesis (Ph.D.)--New York University Tandon School of Engineering, 2018.
504 $a Includes bibliographical references
520 $a Prediction of the upcoming points in a data stream, online prediction , is a fundamental problem in machine learning. In this thesis, we design meta-algorithms that can take any standard online prediction algorithm and provably improve its performance, given the right to refuse to make predictions in some instances. Allowing refusals means that the meta-algorithm may decline to emit a prediction produced by the base algorithm on occasion. We investigate this problem in two different settings.
520 $a First, we assume the data points in the stream are sampled from an exchangeable distribution. Under this assumption, we introduce Conjugate Predictors as a refusing meta-algorithm which guarantees that the error probability of any standard machine learning algorithm is kept below a pre-specified target epsilon. Our approach, based on conformal predictors, refuses less often than state-of-art meta-algorithms, with the level of improvement depending on the characteristics of the base algorithm. We validate our theoretical guarantees and the effectiveness of our approach through experiments on standard machine learning data sets and algorithms, such as k-nearest neighbors and random forests.
520 $a Next, we relax assumptions on the distribution of data and propose a novel meta-algorithm, SafePredict, that works with any base predictor for online data. SafePredict guarantees an arbitrarily chosen error rate, epsilon, on non-refused data points. The SafePredict error bound does not rely on any assumptions on the data distribution or the base predictor. When the base predictor happens not to exceed the target error rate epsilon, SafePredict refuses only a finite number of times. When the error rate of the base predictor changes through time, SafePredict makes use of a weight-shifting heuristic that adapts to these changes without knowing when the changes occur yet still maintains the correctness guarantee. Empirical results show that (i) SafePredict compares favorably with state-of-the-art confidence based refusal mechanisms which fail to offer robust error guarantees, and (ii) combining SafePredict with such refusal mechanisms can in many cases further reduce the number of refusals.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Artificial intelligence. $3 559380
650 4 $a Statistics. $3 556824
655 7 $a Electronic books. $2 local $3 554714
690 $a 0800
690 $a 0463
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a New York University Tandon School of Engineering. $b Electrical and Computer Engineering. $3 1190679
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10641615 $z click for full text (PQDT)