國立虎尾科技大學 |

Reliable and Adaptive Stochastic Optimization in the Face of Messy Data.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Reliable and Adaptive Stochastic Optimization in the Face of Messy Data./
作者:	Xie, Miaolan.
面頁冊數:	1 online resource (151 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: A.
Contained By:	Dissertations Abstracts International85-12A.
標題:	Mathematics. -
電子資源:	click for full text (PQDT)
ISBN:	9798382842257

Reliable and Adaptive Stochastic Optimization in the Face of Messy Data.
Xie, Miaolan.

Reliable and Adaptive Stochastic Optimization in the Face of Messy Data. - 1 online resource (151 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: A.

Thesis (Ph.D.)--Cornell University, 2024.

Includes bibliographical references

Solving real-world stochastic optimization problems (e.g., in machine learning) presents two key challenges: the messiness of real-world data, which can be noisy, biased, or corrupted due to factors like outliers, distribution shifts, and even adversarial attacks; and the laborious, time-intensive requirement of manually tuning step sizes in many existing algorithms.I study stochastic adaptive optimization algorithms under a simple, common framework. The algorithms in this framework avoid the need for manual step size tuning by adaptively adjusting it in each iteration based on the algorithm's progress. To address the issue of messy data, the framework only assumes access to function-related information through probabilistic oracles, which may be biased and corrupted. This framework is very general, encompassing a wide range of algorithms, and is applicable to multiple problem settings, such as expected loss minimization in machine learning, simulation optimization, and derivative-free optimization. We establish iteration complexity bounds for two algorithms within it - stochastic adaptive step search and stochastic adaptive cubic-regularized Newton method - under reasonable oracle conditions. Additionally, we derive a meta-theorem to bound the sample complexity for any algorithm in the framework.

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

Mode of access: World Wide Web

ISBN: 9798382842257Subjects--Topical Terms:

527692
Mathematics.
Subjects--Index Terms:

Mathematical optimizationIndex Terms--Genre/Form:

554714
Electronic books.

Reliable and Adaptive Stochastic Optimization in the Face of Messy Data.
LDR:02731ntm a22004097 4500 001 1151738
005 20241118085748.5
006 m o d
007 cr mn ---uuuuu
008 250605s2024 xx obm 000 0 eng d
020 $a 9798382842257
035 $a (MiAaPQ)AAI31242760
035 $a AAI31242760
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Xie, Miaolan. $3 1478559
245 1 0 $a Reliable and Adaptive Stochastic Optimization in the Face of Messy Data.
264 0 $c 2024
300 $a 1 online resource (151 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: 85-12, Section: A.
500 $a Advisor: Scheinberg, Katya.
502 $a Thesis (Ph.D.)--Cornell University, 2024.
504 $a Includes bibliographical references
520 $a Solving real-world stochastic optimization problems (e.g., in machine learning) presents two key challenges: the messiness of real-world data, which can be noisy, biased, or corrupted due to factors like outliers, distribution shifts, and even adversarial attacks; and the laborious, time-intensive requirement of manually tuning step sizes in many existing algorithms.I study stochastic adaptive optimization algorithms under a simple, common framework. The algorithms in this framework avoid the need for manual step size tuning by adaptively adjusting it in each iteration based on the algorithm's progress. To address the issue of messy data, the framework only assumes access to function-related information through probabilistic oracles, which may be biased and corrupted. This framework is very general, encompassing a wide range of algorithms, and is applicable to multiple problem settings, such as expected loss minimization in machine learning, simulation optimization, and derivative-free optimization. We establish iteration complexity bounds for two algorithms within it - stochastic adaptive step search and stochastic adaptive cubic-regularized Newton method - under reasonable oracle conditions. Additionally, we derive a meta-theorem to bound the sample complexity for any algorithm in the framework.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Mathematics. $3 527692
650 4 $a Computer science. $3 573171
650 4 $a Information science. $3 561178
653 $a Mathematical optimization
653 $a Nonlinear optimization
653 $a Simulation optimization
653 $a Stochastic optimization
653 $a Messy data
655 7 $a Electronic books. $2 local $3 554714
690 $a 0796
690 $a 0984
690 $a 0723
690 $a 0405
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Cornell University. $b Operations Research and Information Engineering. $3 1466270
773 0 $t Dissertations Abstracts International $g 85-12A.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31242760 $z click for full text (PQDT)