On the sample complexity of graphical model selection from non-stationary samples

Nguyen Q. Tran; Alexander Jung

doi:10.1109/ICASSP.2018.8462689

On the sample complexity of graphical model selection from non-stationary samples

Nguyen Q. Tran
, Alexander Jung

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

3 Citations (Scopus)

Abstract

We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed samples are modeled as a zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This includes the case where observations form stationary or underspread processes. We derive a sufficient condition on the required sample size by analyzing a simple sparse neighborhood regression method.

Original language	English
Title of host publication	2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
Publisher	IEEE
Pages	6314-6317
Number of pages	4
Volume	2018-April
ISBN (Print)	9781538646588
DOIs	https://doi.org/10.1109/ICASSP.2018.8462689
Publication status	Published - 10 Sept 2018
MoE publication type	A4 Conference publication
Event	IEEE International Conference on Acoustics, Speech, and Signal Processing - Calgary, Canada Duration: 15 Apr 2018 → 20 Apr 2018 https://2018.ieeeicassp.org/

Conference

Conference	IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP
Country/Territory	Canada
City	Calgary
Period	15/04/2018 → 20/04/2018
Internet address	https://2018.ieeeicassp.org/

Keywords

Graphical model selection
High-dimensional statistics
Neighborhood regression
Sparsity

Access to Document

10.1109/ICASSP.2018.8462689

https://arxiv.org/abs/1701.04724

Cite this

@inproceedings{d5ce27011d2842f2a1b6bffb3f3a5406,

title = "On the sample complexity of graphical model selection from non-stationary samples",

abstract = "We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed samples are modeled as a zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This includes the case where observations form stationary or underspread processes. We derive a sufficient condition on the required sample size by analyzing a simple sparse neighborhood regression method.",

keywords = "Graphical model selection, High-dimensional statistics, Neighborhood regression, Sparsity",

author = "Tran, \{Nguyen Q.\} and Alexander Jung",

year = "2018",

month = sep,

day = "10",

doi = "10.1109/ICASSP.2018.8462689",

language = "English",

isbn = "9781538646588",

volume = "2018-April",

pages = "6314--6317",

booktitle = "2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP ; Conference date: 15-04-2018 Through 20-04-2018",

url = "https://2018.ieeeicassp.org/",

}

Tran, NQ & Jung, A 2018, On the sample complexity of graphical model selection from non-stationary samples. in 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. vol. 2018-April, 8462689, IEEE, pp. 6314-6317, IEEE International Conference on Acoustics, Speech, and Signal Processing, Calgary, Alberta, Canada, 15/04/2018. https://doi.org/10.1109/ICASSP.2018.8462689

On the sample complexity of graphical model selection from non-stationary samples. / Tran, Nguyen Q.; Jung, Alexander.
2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings. Vol. 2018-April IEEE, 2018. p. 6314-6317 8462689.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - On the sample complexity of graphical model selection from non-stationary samples

AU - Tran, Nguyen Q.

AU - Jung, Alexander

PY - 2018/9/10

Y1 - 2018/9/10

N2 - We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed samples are modeled as a zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This includes the case where observations form stationary or underspread processes. We derive a sufficient condition on the required sample size by analyzing a simple sparse neighborhood regression method.

AB - We characterize the sample size required for accurate graphical model selection from non-stationary samples. The observed samples are modeled as a zero-mean Gaussian random process whose samples are uncorrelated but have different covariance matrices. This includes the case where observations form stationary or underspread processes. We derive a sufficient condition on the required sample size by analyzing a simple sparse neighborhood regression method.

KW - Graphical model selection

KW - High-dimensional statistics

KW - Neighborhood regression

KW - Sparsity

UR - https://www.scopus.com/pages/publications/85053845615

UR - https://ieeexplore.ieee.org/document/8462689

U2 - 10.1109/ICASSP.2018.8462689

DO - 10.1109/ICASSP.2018.8462689

M3 - Conference article in proceedings

AN - SCOPUS:85053845615

SN - 9781538646588

VL - 2018-April

SP - 6314

EP - 6317

BT - 2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings

PB - IEEE

T2 - IEEE International Conference on Acoustics, Speech, and Signal Processing

Y2 - 15 April 2018 through 20 April 2018

ER -

On the sample complexity of graphical model selection from non-stationary samples

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this