國立虎尾科技大學 |

Provable and Practical Algorithms for Non-Convex Problems in Machine Learning.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Provable and Practical Algorithms for Non-Convex Problems in Machine Learning./
作者:	Yuan, Yang.
面頁冊數:	1 online resource (204 pages)
附註:	Source: Dissertation Abstracts International, Volume: 79-10(E), Section: B.
Contained By:	Dissertation Abstracts International79-10B(E).
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9780438026636

Provable and Practical Algorithms for Non-Convex Problems in Machine Learning.
Yuan, Yang.

Provable and Practical Algorithms for Non-Convex Problems in Machine Learning. - 1 online resource (204 pages)

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

Thesis (Ph.D.)--Cornell University, 2018.

Includes bibliographical references

Machine learning has become one of the most exciting research areas in the world, with various applications. However, there exists a noticeable gap between theory and practice. On one hand, a simple algorithm like stochastic gradient descent (SGD) works very well in practice, without satisfactory theoretical explanations. On the other hand, the algorithms analyzed in the theoretical machine learning literature, although with solid guarantees, tend to be less efficient compared with the techniques widely used in practice, which are usually hand tuned or ad hoc based on intuition.

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

Mode of access: World Wide Web

ISBN: 9780438026636Subjects--Topical Terms:

573171
Computer science.
Index Terms--Genre/Form:

554714
Electronic books.

Provable and Practical Algorithms for Non-Convex Problems in Machine Learning.
LDR:02665ntm a2200361Ki 4500 001 916913
005 20180928111503.5
006 m o u
007 cr mn||||a|a||
008 190606s2018 xx obm 000 0 eng d
020 $a 9780438026636
035 $a (MiAaPQ)AAI10814646
035 $a (MiAaPQ)cornellgrad:10809
035 $a AAI10814646
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Yuan, Yang. $3 1190782
245 1 0 $a Provable and Practical Algorithms for Non-Convex Problems in Machine Learning.
264 0 $c 2018
300 $a 1 online resource (204 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 Adviser: Robert David Kleinberg.
502 $a Thesis (Ph.D.)--Cornell University, 2018.
504 $a Includes bibliographical references
520 $a Machine learning has become one of the most exciting research areas in the world, with various applications. However, there exists a noticeable gap between theory and practice. On one hand, a simple algorithm like stochastic gradient descent (SGD) works very well in practice, without satisfactory theoretical explanations. On the other hand, the algorithms analyzed in the theoretical machine learning literature, although with solid guarantees, tend to be less efficient compared with the techniques widely used in practice, which are usually hand tuned or ad hoc based on intuition.
520 $a This dissertation is about bridging the gap between theory and practice from two directions. The first direction is "practice to theory", i.e., to explain and analyze the existing algorithms and empirical observations in machine learning. Along this direction, we provide sufficient conditions for SGD to escape saddle points and local minima, as well as SGD dynamics analysis for the two-layer neural network with ReLU activation.
520 $a The other direction is "theory to practice", i.e., using theoretical tools to obtain new, better and practical algorithms. Along this direction, we introduce a new algorithm Harmonica that uses Fourier analysis and compressed sensing for tuning hyperparameters. Harmonica supports parallel sampling and works well for tuning neural networks with more than 30 hyperparameters.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Artificial intelligence. $3 559380
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0800
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Cornell University. $b Computer Science. $3 1179602
773 0 $t Dissertation Abstracts International $g 79-10B(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10814646 $z click for full text (PQDT)