國立虎尾科技大學 |

Robust Estimation and Distribution-Free Inference for Supervised Learning.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Robust Estimation and Distribution-Free Inference for Supervised Learning./
Author:	Lee, Yonghoon.
Description:	1 online resource (135 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 84-12, Section: B.
Contained By:	Dissertations Abstracts International84-12B.
Subject:	Statistics. -
Online resource:	click for full text (PQDT)
ISBN:	9798379706227

Robust Estimation and Distribution-Free Inference for Supervised Learning.
Lee, Yonghoon.

Robust Estimation and Distribution-Free Inference for Supervised Learning. - 1 online resource (135 pages)

Source: Dissertations Abstracts International, Volume: 84-12, Section: B.

Thesis (Ph.D.)--The University of Chicago, 2023.

Includes bibliographical references

We discuss problems where we have limited access to the information of underlying distribution of training data, which can be caused by imperfect data or insufficient prior knowledge.We first look into the binary classification problem, in the setting where the label observations are corrupted by noise. We establish that corruption acts as a form of regularization, and we compute precise upper bounds on estimation error in the presence of corruption. Our results suggest that the presence of corrupted data points is beneficial up to a small fraction of the total sample, scaling with the square root of the sample size.Next, we study the regression problem in the distribution-free setting. We show that there are three regimes in terms of the possibility of meaningful inference, which are characterized by the `effective support size' of the feature distribution. Our result implies that there exists a counterintuitive in-between regime where we can still expect to obtain meaningful inference for a future input even when it is unlikely to have a value we have observed before.We also develop distribution-free methods for predictive inference with hierarchically structured datasets. For the special case where we have i.i.d. repeated measurements, we propose to bound the expected squared conditional miscoverage rate in order to have a better control of the conditional coverage, and extend existing methods to construct distribution-free prediction sets that achieve the bound.

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

Mode of access: World Wide Web

ISBN: 9798379706227Subjects--Topical Terms:

556824
Statistics.
Subjects--Index Terms:

Distribution-free inferenceIndex Terms--Genre/Form:

554714
Electronic books.

Robust Estimation and Distribution-Free Inference for Supervised Learning.
LDR:02796ntm a22003617 4500 001 1145247
005 20240618081759.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798379706227
035 $a (MiAaPQ)AAI30423286
035 $a AAI30423286
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Lee, Yonghoon. $3 1470502
245 1 0 $a Robust Estimation and Distribution-Free Inference for Supervised Learning.
264 0 $c 2023
300 $a 1 online resource (135 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: 84-12, Section: B.
500 $a Advisor: Barber, Rina.
502 $a Thesis (Ph.D.)--The University of Chicago, 2023.
504 $a Includes bibliographical references
520 $a We discuss problems where we have limited access to the information of underlying distribution of training data, which can be caused by imperfect data or insufficient prior knowledge.We first look into the binary classification problem, in the setting where the label observations are corrupted by noise. We establish that corruption acts as a form of regularization, and we compute precise upper bounds on estimation error in the presence of corruption. Our results suggest that the presence of corrupted data points is beneficial up to a small fraction of the total sample, scaling with the square root of the sample size.Next, we study the regression problem in the distribution-free setting. We show that there are three regimes in terms of the possibility of meaningful inference, which are characterized by the `effective support size' of the feature distribution. Our result implies that there exists a counterintuitive in-between regime where we can still expect to obtain meaningful inference for a future input even when it is unlikely to have a value we have observed before.We also develop distribution-free methods for predictive inference with hierarchically structured datasets. For the special case where we have i.i.d. repeated measurements, we propose to bound the expected squared conditional miscoverage rate in order to have a better control of the conditional coverage, and extend existing methods to construct distribution-free prediction sets that achieve the bound.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Statistics. $3 556824
650 4 $a Applied mathematics. $3 1069907
653 $a Distribution-free inference
653 $a Nonparametric statistics
653 $a Robust estimation
655 7 $a Electronic books. $2 local $3 554714
690 $a 0463
690 $a 0364
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a The University of Chicago. $b Statistics. $3 1180881
773 0 $t Dissertations Abstracts International $g 84-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30423286 $z click for full text (PQDT)