Subspace learning with partial information

Alon Gonen; Dan Rosenbaum; Yonina C. Eldar; Shai Shalev-Shwartz

Subspace learning with partial information

Alon Gonen, Dan Rosenbaum, Yonina C. Eldar, Shai Shalev-Shwartz

Research output: Contribution to journal › Article › peer-review

Abstract

The goal of subspace learning is to find a k-dimensional subspace of ℝ^d, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe r ≤ d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity.

Original language	English
Journal	Journal of Machine Learning Research
Volume	17
State	Published - 1 Apr 2016
Externally published	Yes

Bibliographical note

Publisher Copyright:
©2016 Alon Gonen, Dan Rosenbaum, Yonina C. Eldar and Shai Shalev-Shwartz.

Keywords

Budgeted learning
Learning theory
Learning with partial information
Principal components analysis
Statistical learning

ASJC Scopus subject areas

Software
Control and Systems Engineering
Statistics and Probability
Artificial Intelligence

Cite this

@article{ea3b5c4dc9184b05b98d0e58752c0c61,

title = "Subspace learning with partial information",

abstract = "The goal of subspace learning is to find a k-dimensional subspace of ℝd, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe r ≤ d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity.",

keywords = "Budgeted learning, Learning theory, Learning with partial information, Principal components analysis, Statistical learning",

author = "Alon Gonen and Dan Rosenbaum and Eldar, {Yonina C.} and Shai Shalev-Shwartz",

note = "Publisher Copyright: {\textcopyright}2016 Alon Gonen, Dan Rosenbaum, Yonina C. Eldar and Shai Shalev-Shwartz.",

year = "2016",

month = apr,

day = "1",

language = "English",

volume = "17",

journal = "Journal of Machine Learning Research",

issn = "1532-4435",

publisher = "Microtome Publishing",

}

TY - JOUR

T1 - Subspace learning with partial information

AU - Gonen, Alon

AU - Rosenbaum, Dan

AU - Eldar, Yonina C.

AU - Shalev-Shwartz, Shai

PY - 2016/4/1

Y1 - 2016/4/1

N2 - The goal of subspace learning is to find a k-dimensional subspace of ℝd, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe r ≤ d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity.

AB - The goal of subspace learning is to find a k-dimensional subspace of ℝd, such that the expected squared distance between instance vectors and the subspace is as small as possible. In this paper we study subspace learning in a partial information setting, in which the learner can only observe r ≤ d attributes from each instance vector. We propose several efficient algorithms for this task, and analyze their sample complexity.

KW - Budgeted learning

KW - Learning theory

KW - Learning with partial information

KW - Principal components analysis

KW - Statistical learning

UR - http://www.scopus.com/inward/record.url?scp=84979888115&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84979888115

SN - 1532-4435

VL - 17

JO - Journal of Machine Learning Research

JF - Journal of Machine Learning Research

ER -

Subspace learning with partial information

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this