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

Some Results in High Dimensional Sta...

Verchand, Kabir Aladin,

FindBook

Google Book

Amazon

博客來

Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data // Kabir Aladin Verchand.
作者:	Verchand, Kabir Aladin,
面頁冊數:	1 electronic resource (386 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-04, Section: B.
Contained By:	Dissertations Abstracts International85-04B.
標題:	Sparsity. -
電子資源:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615141
ISBN:	9798380470094

Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data /
Verchand, Kabir Aladin,

Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data /Kabir Aladin Verchand. - 1 electronic resource (386 pages)

Source: Dissertations Abstracts International, Volume: 85-04, Section: B.

We study two problems at the interface between statistics and computation. In the first part of this thesis, we consider the problem of fitting a model to data by applying an iterative algorithm to perform empirical risk minimization. While the choice of iterative algorithm determines both the speed with which a fitted model is produced as well as the statistical quality of the produced model, the process of algorithm selection is often performed in a heuristic manner: via either expensive trial-and-error or appeal to (potentially) conservative worst case efficiency estimates. Motivated by this, we develop a framework-based on Gaussian comparison inequalities-to rigorously compare and contrast different iterative procedures to perform empirical risk minimization in an average case setting. In turn, we use this framework to demonstrate concrete separations in the convergence behavior of several iterative algorithms as well as to reveal some nonstandard convergence phenomena.In the second part of this thesis, we turn to studying parametric models with missing data in high dimensions. While this problem is well understood in the classical fixed dimension and infinite sample scaling, the situation changes drastically when the data is high dimensional. First, the high dimensional nature of the problem-which ensures that most samples contain missing entries- removes a complete case analysis from the statistician's toolbox. Second, the log-likelihood may be nonconcave in which case maximum likelihood estimation may prove computationally infeasible. Motivated by these issues, we study imputation-based methodology. In particular, we show that conditional mean imputation followed by a complete data method yields minimax optimal estimators in the linear model. We then show that the situation is quite different in the logistic model: in a stylized setting, conditional mean imputation can yield inconsistent estimators which nonetheless match the (Bayes) optimal prediction error.

English

ISBN: 9798380470094Subjects--Topical Terms:

3680690
Sparsity.

Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data /
LDR:03407nmm a22003853i 4500 001 2396193
005 20250522083208.5
006 m o d
007 cr|nu||||||||
008 251215s2023 miu||||||m |||||||eng d
020 $a 9798380470094
035 $a (MiAaPQD)AAI30615141
035 $a (MiAaPQD)STANFORDqg055vr1907
035 $a AAI30615141
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Verchand, Kabir Aladin, $e author. $3 3765819
245 1 0 $a Some Results in High Dimensional Statistics: Iterative Algorithms and Regression with Missing Data / $c Kabir Aladin Verchand.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 1 electronic resource (386 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: 85-04, Section: B.
500 $a Advisors: Duchi, John; Wootters, Mary; Montanari, Andrea Committee members: Bent, Stacey F.
502 $b Ph.D. $c Stanford University $d 2023.
520 $a We study two problems at the interface between statistics and computation. In the first part of this thesis, we consider the problem of fitting a model to data by applying an iterative algorithm to perform empirical risk minimization. While the choice of iterative algorithm determines both the speed with which a fitted model is produced as well as the statistical quality of the produced model, the process of algorithm selection is often performed in a heuristic manner: via either expensive trial-and-error or appeal to (potentially) conservative worst case efficiency estimates. Motivated by this, we develop a framework-based on Gaussian comparison inequalities-to rigorously compare and contrast different iterative procedures to perform empirical risk minimization in an average case setting. In turn, we use this framework to demonstrate concrete separations in the convergence behavior of several iterative algorithms as well as to reveal some nonstandard convergence phenomena.In the second part of this thesis, we turn to studying parametric models with missing data in high dimensions. While this problem is well understood in the classical fixed dimension and infinite sample scaling, the situation changes drastically when the data is high dimensional. First, the high dimensional nature of the problem-which ensures that most samples contain missing entries- removes a complete case analysis from the statistician's toolbox. Second, the log-likelihood may be nonconcave in which case maximum likelihood estimation may prove computationally infeasible. Motivated by these issues, we study imputation-based methodology. In particular, we show that conditional mean imputation followed by a complete data method yields minimax optimal estimators in the linear model. We then show that the situation is quite different in the logistic model: in a stylized setting, conditional mean imputation can yield inconsistent estimators which nonetheless match the (Bayes) optimal prediction error.
546 $a English
590 $a School code: 0212
650 4 $a Sparsity. $3 3680690
650 4 $a Missing data. $3 3697670
650 4 $a Recipes. $3 1009569
650 4 $a Theorems. $3 3686073
650 4 $a Neighborhoods. $3 993475
650 4 $a Mathematics. $3 515831
690 $a 0405
710 2 $a Stanford University. $e degree granting institution. $3 3765820
720 1 $a Duchi, John $e degree supervisor.
720 1 $a Wootters, Mary $e degree supervisor.
720 1 $a Montanari, Andrea $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-04B.
790 $a 0212
791 $a Ph.D.
792 $a 2023
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30615141