國立虎尾科技大學 |

Recent Developments in Robust Statistics.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Recent Developments in Robust Statistics./
Author:	Cherapanamjeri, Yeshwanth.
Description:	1 online resource (84 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
Subject:	Computer science. -
Online resource:	click for full text (PQDT)
ISBN:	9798380366298

Recent Developments in Robust Statistics.
Cherapanamjeri, Yeshwanth.

Recent Developments in Robust Statistics. - 1 online resource (84 pages)

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--University of California, Berkeley, 2023.

Includes bibliographical references

The design of statistical estimators robust to outliers has been a mainstay of statistical research through the past six decades. These techniques are even more prescient in the contemporary landscape where large-scale machine learning systems are deployed in increasingly noisy and adaptive environments. In this thesis, we consider the task of building such an estimator for arguably the simplest possible statistical estimation problem - that of mean estimation. There is surprisingly little understanding of the computational and statistical limits of estimation and the trade-offs incurred even for this relatively simple setting. We make progress on this problem along three complementary axes.Our first contribution is a simple algorithmic framework for constructing robust estimators. Our framework allows for a significant speed-up over prior approaches for mean estimation while also allowing for easy extensibility to other statistical estimation tasks where it achieves state-of-the-art performance.Secondly, we investigate the statistical boundaries of mean estimation where we demonstrate the necessary statistical degradation incurred in extremely heavy-tailed scenarios. While prior work showed that estimation could be performed as well as if one had access to Guassian data, we establish that this is no longer true when the data possesses heavier tails. We provide lower bounds which exhibit this degradation and an (efficient) algorithm matching them.Lastly, we consider the stability of these estimators to natural transformations of the data. Inspired by the empirical mean, classical work constructed estimators equivariant to affine transformations. These works, however, lacked the strong quantitative performance of more recent approaches. We demonstrate that such trade-offs are in fact necessary by constructing novel lower bounds for affine-equivariant estimators. We then show that classical estimators are quantitatively deficient even in this restricted class and devise an estimator based on a novel notion of a high-dimensional median which matches the lower bound.

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

Mode of access: World Wide Web

ISBN: 9798380366298Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

Machine learningIndex Terms--Genre/Form:

554714
Electronic books.

Recent Developments in Robust Statistics.
LDR:03452ntm a22003857 4500 001 1147539
005 20240909103807.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380366298
035 $a (MiAaPQ)AAI30632930
035 $a AAI30632930
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Cherapanamjeri, Yeshwanth. $3 1473296
245 1 0 $a Recent Developments in Robust Statistics.
264 0 $c 2023
300 $a 1 online resource (84 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: 85-03, Section: B.
500 $a Advisor: Bartlett, Peter.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2023.
504 $a Includes bibliographical references
520 $a The design of statistical estimators robust to outliers has been a mainstay of statistical research through the past six decades. These techniques are even more prescient in the contemporary landscape where large-scale machine learning systems are deployed in increasingly noisy and adaptive environments. In this thesis, we consider the task of building such an estimator for arguably the simplest possible statistical estimation problem - that of mean estimation. There is surprisingly little understanding of the computational and statistical limits of estimation and the trade-offs incurred even for this relatively simple setting. We make progress on this problem along three complementary axes.Our first contribution is a simple algorithmic framework for constructing robust estimators. Our framework allows for a significant speed-up over prior approaches for mean estimation while also allowing for easy extensibility to other statistical estimation tasks where it achieves state-of-the-art performance.Secondly, we investigate the statistical boundaries of mean estimation where we demonstrate the necessary statistical degradation incurred in extremely heavy-tailed scenarios. While prior work showed that estimation could be performed as well as if one had access to Guassian data, we establish that this is no longer true when the data possesses heavier tails. We provide lower bounds which exhibit this degradation and an (efficient) algorithm matching them.Lastly, we consider the stability of these estimators to natural transformations of the data. Inspired by the empirical mean, classical work constructed estimators equivariant to affine transformations. These works, however, lacked the strong quantitative performance of more recent approaches. We demonstrate that such trade-offs are in fact necessary by constructing novel lower bounds for affine-equivariant estimators. We then show that classical estimators are quantitatively deficient even in this restricted class and devise an estimator based on a novel notion of a high-dimensional median which matches the lower bound.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Statistics. $3 556824
653 $a Machine learning
653 $a Natural transformations
653 $a Guassian data
653 $a Statistical estimation problem
653 $a Adaptive environments
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0463
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Computer Science. $3 1179511
773 0 $t Dissertations Abstracts International $g 85-03B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30632930 $z click for full text (PQDT)