Deep robust regression

Tzvi Diskin; Gordana Draskovic; Frederic Pascal; Ami Wiesel

doi:10.1109/CAMSAP.2017.8313200

Deep robust regression

Tzvi Diskin, Gordana Draskovic, Frederic Pascal, Ami Wiesel

The Rachel and Selim Benin School of Engineering and Computer Science

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

8 Scopus citations

Abstract

In this paper, we consider the use of deep neural networks in the context of robust regression. We address the standard linear model with observations that are corrupted by outliers. We build upon Huber's robust regression and the classical least trimmed squares estimator, and propose a deep neural network that generalizes both and provides high accuracy with low computational complexity. The network is trained for arbitrary linear models using a single training phase. Numerical experiments with synthetic data demonstrate that the network can handle on a large range of Signal-to-Noise Ratio (SNR) and is robust to different types of outliers.

Original language	American English
Title of host publication	2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1-5
Number of pages	5
ISBN (Electronic)	9781538612514
DOIs	https://doi.org/10.1109/CAMSAP.2017.8313200
State	Published - 9 Mar 2018
Event	7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017 - Curacao Duration: 10 Dec 2017 → 13 Dec 2017

Publication series

Name	2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017
Volume	2017-December

Conference

Conference	7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017
City	Curacao
Period	10/12/17 → 13/12/17

Bibliographical note

Funding Information:
This research was partly supported by ISF grant 1339/15.

Publisher Copyright:
© 2017 IEEE.

Keywords

Deep Learning
Neural Networks
Robust Regression

Access to Document

10.1109/CAMSAP.2017.8313200

Cite this

Diskin, T., Draskovic, G., Pascal, F., & Wiesel, A. (2018). Deep robust regression. In 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017 (pp. 1-5). Article 8313200 (2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017; Vol. 2017-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CAMSAP.2017.8313200

Diskin, Tzvi ; Draskovic, Gordana ; Pascal, Frederic et al. / Deep robust regression. 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-5 (2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017).

@inproceedings{e53a565caa3c4efca46cae429c90a5cd,

title = "Deep robust regression",

abstract = "In this paper, we consider the use of deep neural networks in the context of robust regression. We address the standard linear model with observations that are corrupted by outliers. We build upon Huber's robust regression and the classical least trimmed squares estimator, and propose a deep neural network that generalizes both and provides high accuracy with low computational complexity. The network is trained for arbitrary linear models using a single training phase. Numerical experiments with synthetic data demonstrate that the network can handle on a large range of Signal-to-Noise Ratio (SNR) and is robust to different types of outliers.",

keywords = "Deep Learning, Neural Networks, Robust Regression",

author = "Tzvi Diskin and Gordana Draskovic and Frederic Pascal and Ami Wiesel",

note = "Funding Information: This research was partly supported by ISF grant 1339/15. Publisher Copyright: {\textcopyright} 2017 IEEE.; 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017 ; Conference date: 10-12-2017 Through 13-12-2017",

year = "2018",

month = mar,

day = "9",

doi = "10.1109/CAMSAP.2017.8313200",

language = "American English",

series = "2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017",

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

pages = "1--5",

booktitle = "2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017",

address = "United States",

}

Diskin, T, Draskovic, G, Pascal, F & Wiesel, A 2018, Deep robust regression. in 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017., 8313200, 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017, vol. 2017-December, Institute of Electrical and Electronics Engineers Inc., pp. 1-5, 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017, Curacao, 10/12/17. https://doi.org/10.1109/CAMSAP.2017.8313200

Deep robust regression. / Diskin, Tzvi; Draskovic, Gordana; Pascal, Frederic et al.
2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-5 8313200 (2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017; Vol. 2017-December).

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

TY - GEN

T1 - Deep robust regression

AU - Diskin, Tzvi

AU - Draskovic, Gordana

AU - Pascal, Frederic

AU - Wiesel, Ami

PY - 2018/3/9

Y1 - 2018/3/9

N2 - In this paper, we consider the use of deep neural networks in the context of robust regression. We address the standard linear model with observations that are corrupted by outliers. We build upon Huber's robust regression and the classical least trimmed squares estimator, and propose a deep neural network that generalizes both and provides high accuracy with low computational complexity. The network is trained for arbitrary linear models using a single training phase. Numerical experiments with synthetic data demonstrate that the network can handle on a large range of Signal-to-Noise Ratio (SNR) and is robust to different types of outliers.

AB - In this paper, we consider the use of deep neural networks in the context of robust regression. We address the standard linear model with observations that are corrupted by outliers. We build upon Huber's robust regression and the classical least trimmed squares estimator, and propose a deep neural network that generalizes both and provides high accuracy with low computational complexity. The network is trained for arbitrary linear models using a single training phase. Numerical experiments with synthetic data demonstrate that the network can handle on a large range of Signal-to-Noise Ratio (SNR) and is robust to different types of outliers.

KW - Deep Learning

KW - Neural Networks

KW - Robust Regression

UR - http://www.scopus.com/inward/record.url?scp=85051146010&partnerID=8YFLogxK

U2 - 10.1109/CAMSAP.2017.8313200

DO - 10.1109/CAMSAP.2017.8313200

M3 - Conference contribution

AN - SCOPUS:85051146010

T3 - 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017

SP - 1

EP - 5

BT - 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th IEEE International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017

Y2 - 10 December 2017 through 13 December 2017

ER -

Diskin T, Draskovic G, Pascal F, Wiesel A. Deep robust regression. In 2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-5. 8313200. (2017 IEEE 7th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, CAMSAP 2017). doi: 10.1109/CAMSAP.2017.8313200

Deep robust regression

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this