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

FindBook

Google Book

Amazon

博客來

Statistical Learning Under Resource Constraints.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Statistical Learning Under Resource Constraints./
作者:	Tai, Kai Sheng.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	190 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
Contained By:	Dissertations Abstracts International83-05B.
標題:	Sparsity. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28827985
ISBN:	9798494462107

Statistical Learning Under Resource Constraints.
Tai, Kai Sheng.

Statistical Learning Under Resource Constraints. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 190 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: B.

Thesis (Ph.D.)--Stanford University, 2021.

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

Statistical learning algorithms are an increasingly prevalent component of modern software systems. As such, the design of learning algorithms themselves must take into account the constraints imposed by resource-constrained applications. This dissertation explores resource-constrained learning from two distinct perspectives: learning with limited memory and learning with limited labeled data. In Part I, we consider the challenge of learning with limited memory, a constraint that frequently arises in the context of learning on mobile or embedded devices. First, we describe a randomized sketching algorithm that learns a linear classifier in a compressed, space-efficient form---i.e., by storing far fewer parameters than the dimension of the input features. Unlike typical feature hashing approaches, our method allows for the efficient recovery of the largest magnitude weights in the learned classifier, thus facilitating model interpretation and enabling several memory-efficient stream processing applications. Next, we shift our focus to unsupervised learning, where we study low-rank matrix and tensor factorization on compressed data. In this setting, we establish conditions under which a factorization computed on compressed data can be used to provably recover factors in the original, high-dimensional space. In Part II, we study the statistical constraint of learning with limited labeled data. We first present Equivariant Transformer layers, a family of differentiable image-to-image mappings that improve sample efficiency by directly incorporating prior knowledge on transformation invariances into their architecture. We then discuss a self-training algorithm for semi-supervised learning, where a small number of labeled examples is supplemented by a large collection of unlabeled data. Our method reinterprets the semi-supervised label assignment process as an optimal transportation problem between examples and classes, the solution to which can be efficiently approximated via Sinkhorn iteration. This formulation subsumes several commonly used label assignment heuristics within a single principled optimization framework.

ISBN: 9798494462107Subjects--Topical Terms:

3680690
Sparsity.

Statistical Learning Under Resource Constraints.
LDR:03314nmm a2200385 4500 001 2349636
005 20230509091134.5
006 m o d
007 cr#unu||||||||
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798494462107
035 $a (MiAaPQ)AAI28827985
035 $a (MiAaPQ)STANFORDmp952br3417
035 $a AAI28827985
040 $a MiAaPQ $c MiAaPQ
100 1 $a Tai, Kai Sheng. $3 3689048
245 1 0 $a Statistical Learning Under Resource Constraints.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 190 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: B.
500 $a Advisor: Valiant, Gregory;Zaharia, Matei;Bailis, Peter.
502 $a Thesis (Ph.D.)--Stanford University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Statistical learning algorithms are an increasingly prevalent component of modern software systems. As such, the design of learning algorithms themselves must take into account the constraints imposed by resource-constrained applications. This dissertation explores resource-constrained learning from two distinct perspectives: learning with limited memory and learning with limited labeled data. In Part I, we consider the challenge of learning with limited memory, a constraint that frequently arises in the context of learning on mobile or embedded devices. First, we describe a randomized sketching algorithm that learns a linear classifier in a compressed, space-efficient form---i.e., by storing far fewer parameters than the dimension of the input features. Unlike typical feature hashing approaches, our method allows for the efficient recovery of the largest magnitude weights in the learned classifier, thus facilitating model interpretation and enabling several memory-efficient stream processing applications. Next, we shift our focus to unsupervised learning, where we study low-rank matrix and tensor factorization on compressed data. In this setting, we establish conditions under which a factorization computed on compressed data can be used to provably recover factors in the original, high-dimensional space. In Part II, we study the statistical constraint of learning with limited labeled data. We first present Equivariant Transformer layers, a family of differentiable image-to-image mappings that improve sample efficiency by directly incorporating prior knowledge on transformation invariances into their architecture. We then discuss a self-training algorithm for semi-supervised learning, where a small number of labeled examples is supplemented by a large collection of unlabeled data. Our method reinterprets the semi-supervised label assignment process as an optimal transportation problem between examples and classes, the solution to which can be efficiently approximated via Sinkhorn iteration. This formulation subsumes several commonly used label assignment heuristics within a single principled optimization framework.
590 $a School code: 0212.
650 4 $a Sparsity. $3 3680690
650 4 $a Wireless networks. $3 1531264
650 4 $a Gene expression. $3 643979
650 4 $a Communication. $3 524709
650 4 $a Decomposition. $3 3561186
650 4 $a Algorithms. $3 536374
650 4 $a Distance learning. $3 3557921
650 4 $a Lie groups. $3 526114
650 4 $a Bioinformatics. $3 553671
650 4 $a Computer science. $3 523869
650 4 $a Electrical engineering. $3 649834
650 4 $a Engineering. $3 586835
650 4 $a Genetics. $3 530508
690 $a 0459
690 $a 0715
690 $a 0984
690 $a 0544
690 $a 0537
690 $a 0369
710 2 $a Stanford University. $3 754827
773 0 $t Dissertations Abstracts International $g 83-05B.
790 $a 0212
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28827985