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

Metric and Tame Geometry in Optimiza...

Tian, Tonghua,

FindBook

Google Book

Amazon

博客來

Metric and Tame Geometry in Optimization /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Metric and Tame Geometry in Optimization // Tonghua Tian.
作者:	Tian, Tonghua,
面頁冊數:	1 electronic resource (199 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
標題:	Theoretical mathematics. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31237872
ISBN:	9798382841472

Metric and Tame Geometry in Optimization /
Tian, Tonghua,

Metric and Tame Geometry in Optimization /Tonghua Tian. - 1 electronic resource (199 pages)

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

Structure in optimization is traditionally studied through variational analysis. Structural results usually require convexity or other regularity conditions. However, contemporary optimization involves problems that lie beyond this traditional scope, especially in machine learning, both in Euclidean space and in non-Euclidean metric spaces. This thesis pursues theories for such problems that reveal underlying geometric structure and aid algorithm design and analysis.A central philosophy in the thesis is to highlight the slope as a tool for capturing first-order information of objectives. This engenders a subgradient-free development: subgradients are indirect in depicting structure and do not extend naturally to non-Euclidean settings. The development focuses on two ideas traditionally studied through subgradients.The first idea is identification: the phenomenon of a set being identified by certain convergent sequences in finite time. By re-interpreting identification via the slope, the thesis extends the idea from Euclidean space to general metric spaces, and establishes results on objective growth rates and necessary conditions for optimization on metric spaces. An extension of identification behavior from discrete-time sequences to continuous-time trajectories is also included.The second idea is the Kurdyka-Lojasiewicz (KL) inequality: a popular tool for convergence analysis in optimization. Defining the KL inequality via the slope reveals its connection with identification, and more importantly its impact on complexity analysis of first-order methods in metric spaces.The prevalence of identifiability and of objectives satisfying the KL inequality is established in the literature from semialgebraic (or, more generally, tame) geometry. Based on the same technique, the thesis presents two other results. The first characterizes the structure of conservative gradient fields, a notion of generalized gradients especially useful in analyzing deep learning methods. The second concerns the generic prevalence of partly smooth set-valued mappings, a type of structure known to be associated with identifiable sets. Furthermore, the thesis gives a short slope-based proof for the fundamental fact that semialgebraic functions possess the KL property.Finally, to unify and relax traditional structural assumptions such as convexity, smoothness, and their compositions, the thesis proposes a new type of implicit structure - smooth approximate convexity. The thesis shows the prevalence of such structure and demonstrates its applicability with a Riemannian optimization example.

English

ISBN: 9798382841472Subjects--Topical Terms:

3173530
Theoretical mathematics.
Subjects--Index Terms:

Euclidean space

Metric and Tame Geometry in Optimization /
LDR:03998nmm a22004333i 4500 001 2438201
005 20251210113944.5
006 m o d
007 cr|nu||||||||
008 261011s2024 miu||||||m |||||||eng d
020 $a 9798382841472
035 $a (MiAaPQD)AAI31237872
035 $a AAI31237872
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Tian, Tonghua, $e author. $0 (orcid)0009-0005-9708-1170 $3 3829436
245 1 0 $a Metric and Tame Geometry in Optimization / $c Tonghua Tian.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (199 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: B.
500 $a Advisors: Lewis, Adrian Committee members: Davis, Damek; Scheinberg, Katya.
502 $b Ph.D. $c Cornell University $d 2024.
520 $a Structure in optimization is traditionally studied through variational analysis. Structural results usually require convexity or other regularity conditions. However, contemporary optimization involves problems that lie beyond this traditional scope, especially in machine learning, both in Euclidean space and in non-Euclidean metric spaces. This thesis pursues theories for such problems that reveal underlying geometric structure and aid algorithm design and analysis.A central philosophy in the thesis is to highlight the slope as a tool for capturing first-order information of objectives. This engenders a subgradient-free development: subgradients are indirect in depicting structure and do not extend naturally to non-Euclidean settings. The development focuses on two ideas traditionally studied through subgradients.The first idea is identification: the phenomenon of a set being identified by certain convergent sequences in finite time. By re-interpreting identification via the slope, the thesis extends the idea from Euclidean space to general metric spaces, and establishes results on objective growth rates and necessary conditions for optimization on metric spaces. An extension of identification behavior from discrete-time sequences to continuous-time trajectories is also included.The second idea is the Kurdyka-Lojasiewicz (KL) inequality: a popular tool for convergence analysis in optimization. Defining the KL inequality via the slope reveals its connection with identification, and more importantly its impact on complexity analysis of first-order methods in metric spaces.The prevalence of identifiability and of objectives satisfying the KL inequality is established in the literature from semialgebraic (or, more generally, tame) geometry. Based on the same technique, the thesis presents two other results. The first characterizes the structure of conservative gradient fields, a notion of generalized gradients especially useful in analyzing deep learning methods. The second concerns the generic prevalence of partly smooth set-valued mappings, a type of structure known to be associated with identifiable sets. Furthermore, the thesis gives a short slope-based proof for the fundamental fact that semialgebraic functions possess the KL property.Finally, to unify and relax traditional structural assumptions such as convexity, smoothness, and their compositions, the thesis proposes a new type of implicit structure - smooth approximate convexity. The thesis shows the prevalence of such structure and demonstrates its applicability with a Riemannian optimization example.
546 $a English
590 $a School code: 0058
650 4 $a Theoretical mathematics. $3 3173530
650 4 $a Applied mathematics. $3 2122814
653 $a Euclidean space
653 $a Tame geometry
653 $a Kurdyka-Lojasiewicz property
653 $a Riemannian optimization
653 $a Metric spaces
690 $a 0796
690 $a 0642
690 $a 0364
710 2 $a Cornell University. $b Operations Research and Information Engineering. $e degree granting institution. $3 3823320
720 1 $a Lewis, Adrian $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 0058
791 $a Ph.D.
792 $a 2024
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31237872