Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method

Mohammad Jamhuri; Imam Mukhlash; Mohammad Isa Irawan

doi:10.1145/3545839.3545842

Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method

Mohammad Jamhuri^*, Imam Mukhlash, Mohammad Isa Irawan

^*Corresponding author for this work

Laboratory of Machine Learning and Big Data

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

Abstract

This paper proposes a new approach to optimizing cost function for binary logistic regression by the Gauss-Newton method. This method was applied to the backpropagation phase as a part of the training process to update the weighted coefficients. To show the performance of the approach, we used two data sets to train the logistic regression model for binary classification problems. Our experiment demonstrated that the proposed methods could perform better than gradient descent for both examples, as we expected. Furthermore, the performance of our approach is more advanced than the classical method, either in speed or accuracy.

Original language	English
Title of host publication	ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics
Publisher	Association for Computing Machinery
Pages	12-16
Number of pages	5
ISBN (Electronic)	9781450396233
DOIs	https://doi.org/10.1145/3545839.3545842
Publication status	Published - 17 Jun 2022
Event	5th International Conference on Mathematics and Statistics, ICoMS 2022 - Paris, France Duration: 17 Jun 2022 → 19 Jun 2022

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	5th International Conference on Mathematics and Statistics, ICoMS 2022
Country/Territory	France
City	Paris
Period	17/06/22 → 19/06/22

Keywords

Gauss-Newton
binary classification
gradient descent
logistic regression

Access to Document

10.1145/3545839.3545842

Cite this

Jamhuri, M., Mukhlash, I., & Irawan, M. I. (2022). Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method. In ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics (pp. 12-16). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3545839.3545842

@inproceedings{eeab0b35c779498c9fc6e66dc71aed5c,

title = "Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method",

abstract = "This paper proposes a new approach to optimizing cost function for binary logistic regression by the Gauss-Newton method. This method was applied to the backpropagation phase as a part of the training process to update the weighted coefficients. To show the performance of the approach, we used two data sets to train the logistic regression model for binary classification problems. Our experiment demonstrated that the proposed methods could perform better than gradient descent for both examples, as we expected. Furthermore, the performance of our approach is more advanced than the classical method, either in speed or accuracy.",

keywords = "Gauss-Newton, binary classification, gradient descent, logistic regression",

author = "Mohammad Jamhuri and Imam Mukhlash and Irawan, {Mohammad Isa}",

note = "Publisher Copyright: {\textcopyright} 2022 ACM.; 5th International Conference on Mathematics and Statistics, ICoMS 2022 ; Conference date: 17-06-2022 Through 19-06-2022",

year = "2022",

month = jun,

day = "17",

doi = "10.1145/3545839.3545842",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "12--16",

booktitle = "ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics",

}

Jamhuri, M, Mukhlash, I & Irawan, MI 2022, Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method. in ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 12-16, 5th International Conference on Mathematics and Statistics, ICoMS 2022, Paris, France, 17/06/22. https://doi.org/10.1145/3545839.3545842

Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method. / Jamhuri, Mohammad; Mukhlash, Imam ; Irawan, Mohammad Isa.
ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics. Association for Computing Machinery, 2022. p. 12-16 (ACM International Conference Proceeding Series).

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

TY - GEN

T1 - Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method

AU - Jamhuri, Mohammad

AU - Mukhlash, Imam

AU - Irawan, Mohammad Isa

PY - 2022/6/17

Y1 - 2022/6/17

N2 - This paper proposes a new approach to optimizing cost function for binary logistic regression by the Gauss-Newton method. This method was applied to the backpropagation phase as a part of the training process to update the weighted coefficients. To show the performance of the approach, we used two data sets to train the logistic regression model for binary classification problems. Our experiment demonstrated that the proposed methods could perform better than gradient descent for both examples, as we expected. Furthermore, the performance of our approach is more advanced than the classical method, either in speed or accuracy.

AB - This paper proposes a new approach to optimizing cost function for binary logistic regression by the Gauss-Newton method. This method was applied to the backpropagation phase as a part of the training process to update the weighted coefficients. To show the performance of the approach, we used two data sets to train the logistic regression model for binary classification problems. Our experiment demonstrated that the proposed methods could perform better than gradient descent for both examples, as we expected. Furthermore, the performance of our approach is more advanced than the classical method, either in speed or accuracy.

KW - Gauss-Newton

KW - binary classification

KW - gradient descent

KW - logistic regression

UR - http://www.scopus.com/inward/record.url?scp=85138428647&partnerID=8YFLogxK

U2 - 10.1145/3545839.3545842

DO - 10.1145/3545839.3545842

M3 - Conference contribution

AN - SCOPUS:85138428647

T3 - ACM International Conference Proceeding Series

SP - 12

EP - 16

BT - ICoMS 2022 - Proceedings of 2022 5th International Conference on Mathematics and Statistics

PB - Association for Computing Machinery

T2 - 5th International Conference on Mathematics and Statistics, ICoMS 2022

Y2 - 17 June 2022 through 19 June 2022

ER -

Performance Improvement of Logistic Regression for Binary Classification by Gauss-Newton Method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this