Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples

Thanh V. Nguyen; Akshay Soni; Chinmay Hegde

doi:10.1109/SampTA45681.2019.9030979

Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples

Thanh V. Nguyen, Akshay Soni, Chinmay Hegde

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In dictionary learning, we seek a collection of atoms that sparsely represent a given set of training samples. While this problem is well-studied, relatively less is known about the more challenging case where the samples are incomplete, i.e., we only observe a fraction of their coordinates. In this paper, we develop and analyze an algorithm to solve this problem, provided that the dictionary satisfies additional low-dimensional structure.

Original language	English (US)
Title of host publication	2019 13th International Conference on Sampling Theory and Applications, SampTA 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728137414
DOIs	https://doi.org/10.1109/SampTA45681.2019.9030979
State	Published - Jul 2019
Event	13th International Conference on Sampling Theory and Applications, SampTA 2019 - Bordeaux, France Duration: Jul 8 2019 → Jul 12 2019

Publication series

Name	2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

Conference

Conference	13th International Conference on Sampling Theory and Applications, SampTA 2019
Country/Territory	France
City	Bordeaux
Period	7/8/19 → 7/12/19

ASJC Scopus subject areas

Statistics and Probability
Signal Processing
Analysis
Statistics, Probability and Uncertainty
Applied Mathematics

Access to Document

10.1109/SampTA45681.2019.9030979

Cite this

Nguyen, T. V., Soni, A., & Hegde, C. (2019). Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples. In 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019 Article 9030979 (2019 13th International Conference on Sampling Theory and Applications, SampTA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SampTA45681.2019.9030979

Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples. / Nguyen, Thanh V.; Soni, Akshay; Hegde, Chinmay.
2019 13th International Conference on Sampling Theory and Applications, SampTA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 9030979 (2019 13th International Conference on Sampling Theory and Applications, SampTA 2019).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Nguyen, TV, Soni, A & Hegde, C 2019, Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples. in 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019., 9030979, 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019, Institute of Electrical and Electronics Engineers Inc., 13th International Conference on Sampling Theory and Applications, SampTA 2019, Bordeaux, France, 7/8/19. https://doi.org/10.1109/SampTA45681.2019.9030979

Nguyen TV, Soni A, Hegde C. Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples. In 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 9030979. (2019 13th International Conference on Sampling Theory and Applications, SampTA 2019). doi: 10.1109/SampTA45681.2019.9030979

@inproceedings{f79a039d422f40778e0bd82fd85622a7,

title = "Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples",

abstract = "In dictionary learning, we seek a collection of atoms that sparsely represent a given set of training samples. While this problem is well-studied, relatively less is known about the more challenging case where the samples are incomplete, i.e., we only observe a fraction of their coordinates. In this paper, we develop and analyze an algorithm to solve this problem, provided that the dictionary satisfies additional low-dimensional structure.",

author = "Nguyen, {Thanh V.} and Akshay Soni and Chinmay Hegde",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 13th International Conference on Sampling Theory and Applications, SampTA 2019 ; Conference date: 08-07-2019 Through 12-07-2019",

year = "2019",

month = jul,

doi = "10.1109/SampTA45681.2019.9030979",

language = "English (US)",

series = "2019 13th International Conference on Sampling Theory and Applications, SampTA 2019",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 13th International Conference on Sampling Theory and Applications, SampTA 2019",

}

TY - GEN

T1 - Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples

AU - Nguyen, Thanh V.

AU - Soni, Akshay

AU - Hegde, Chinmay

PY - 2019/7

Y1 - 2019/7

N2 - In dictionary learning, we seek a collection of atoms that sparsely represent a given set of training samples. While this problem is well-studied, relatively less is known about the more challenging case where the samples are incomplete, i.e., we only observe a fraction of their coordinates. In this paper, we develop and analyze an algorithm to solve this problem, provided that the dictionary satisfies additional low-dimensional structure.

AB - In dictionary learning, we seek a collection of atoms that sparsely represent a given set of training samples. While this problem is well-studied, relatively less is known about the more challenging case where the samples are incomplete, i.e., we only observe a fraction of their coordinates. In this paper, we develop and analyze an algorithm to solve this problem, provided that the dictionary satisfies additional low-dimensional structure.

UR - http://www.scopus.com/inward/record.url?scp=85082861013&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85082861013&partnerID=8YFLogxK

U2 - 10.1109/SampTA45681.2019.9030979

DO - 10.1109/SampTA45681.2019.9030979

M3 - Conference contribution

AN - SCOPUS:85082861013

T3 - 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

BT - 2019 13th International Conference on Sampling Theory and Applications, SampTA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th International Conference on Sampling Theory and Applications, SampTA 2019

Y2 - 8 July 2019 through 12 July 2019

ER -

Tractable Learning of Sparsely Used Dictionaries from Incomplete Samples

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this