東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Statistics Meets Nonconvex Optimizat...

Ma, Cong.

Linked to FindBook

Google Book

Amazon

博客來

Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification./
Author:	Ma, Cong.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	682 p.
Notes:	Source: Dissertations Abstracts International, Volume: 82-02, Section: B.
Contained By:	Dissertations Abstracts International82-02B.
Subject:	Statistics. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27962438
ISBN:	9798662418127

Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification.
Ma, Cong.

Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 682 p.

Source: Dissertations Abstracts International, Volume: 82-02, Section: B.

Thesis (Ph.D.)--Princeton University, 2020.

This item must not be sold to any third party vendors.

In recent years, there has been an explosion of interest in designing fast nonconvex optimization algorithms to solve statistical estimation and learning problems. However, in contrast to convex optimization that has become a real pillar of modern engineering, the theoretical foundations of nonconvex optimization are far from satisfactory, especially in terms of its computational and inferential properties. The main focus of this thesis is therefore to develop a fundamental understanding of nonconvex optimization in statistical estimation and inference. Starting with statistical estimation, we have shown that• vanilla gradient descent, in conjunction with spectral initialization, converges linearly for a family of nonconvex statistical learning problems including phase retrieval, matrix completion, and blind deconvolution;• gradient descent-when initialized randomly-implicitly avoids all the saddle points, thus enabling optimal convergence rates and statistical accuracy at once for the phase retrieval problem.In addition to demonstrating the computational advantages of nonconvex optimization, we also uncover an interesting and inherent connection of nonconvex optimization to convex relaxation: they are essentially equivalent for solving the noisy matrix completion problem. This connection allows us to establish the minimax optimality of convex relaxation vis-a`-vis random noise. Going beyond estimation, we further develop a simple procedure to compensate for the bias of the widely used convex and nonconvex estimators for noisy matrix completion. The resulting de-biased estimators admit nearly precise non-asymptotic distributional characterizations, which in turn enable optimal construction of confidence intervals/regions for, say, the missing entries and the low-rank factors. All of this is achieved via an integrated view of statistics and optimization, which we highlight throughout the thesis.

ISBN: 9798662418127Subjects--Topical Terms:

517247
Statistics.
Subjects--Index Terms:

Statistics

Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification.
LDR:03088nmm a2200349 4500 001 2279406
005 20210817110130.5
008 220723s2020 ||||||||||||||||| ||eng d
020 $a 9798662418127
035 $a (MiAaPQ)AAI27962438
035 $a AAI27962438
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ma, Cong. $3 3557853
245 1 0 $a Statistics Meets Nonconvex Optimization: Computational Efficiency and Uncertainty Quantification.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 682 p.
500 $a Source: Dissertations Abstracts International, Volume: 82-02, Section: B.
500 $a Advisor: Chen, Yuxin;Fan, Jianqing.
502 $a Thesis (Ph.D.)--Princeton University, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a In recent years, there has been an explosion of interest in designing fast nonconvex optimization algorithms to solve statistical estimation and learning problems. However, in contrast to convex optimization that has become a real pillar of modern engineering, the theoretical foundations of nonconvex optimization are far from satisfactory, especially in terms of its computational and inferential properties. The main focus of this thesis is therefore to develop a fundamental understanding of nonconvex optimization in statistical estimation and inference. Starting with statistical estimation, we have shown that• vanilla gradient descent, in conjunction with spectral initialization, converges linearly for a family of nonconvex statistical learning problems including phase retrieval, matrix completion, and blind deconvolution;• gradient descent-when initialized randomly-implicitly avoids all the saddle points, thus enabling optimal convergence rates and statistical accuracy at once for the phase retrieval problem.In addition to demonstrating the computational advantages of nonconvex optimization, we also uncover an interesting and inherent connection of nonconvex optimization to convex relaxation: they are essentially equivalent for solving the noisy matrix completion problem. This connection allows us to establish the minimax optimality of convex relaxation vis-a`-vis random noise. Going beyond estimation, we further develop a simple procedure to compensate for the bias of the widely used convex and nonconvex estimators for noisy matrix completion. The resulting de-biased estimators admit nearly precise non-asymptotic distributional characterizations, which in turn enable optimal construction of confidence intervals/regions for, say, the missing entries and the low-rank factors. All of this is achieved via an integrated view of statistics and optimization, which we highlight throughout the thesis.
590 $a School code: 0181.
650 4 $a Statistics. $3 517247
650 4 $a Operations research. $3 547123
653 $a Statistics
653 $a Nonconvex optimization
653 $a Computational efficiency
653 $a Uncertainty quantification
690 $a 0463
690 $a 0796
710 2 $a Princeton University. $b Operations Research and Financial Engineering. $3 2096743
773 0 $t Dissertations Abstracts International $g 82-02B.
790 $a 0181
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=27962438