Article Per Year (5 Year)
p-Index From 2021 - 2026
1.182
P-Index
This Author published in this journals
All Journal CAUCHY: Jurnal Matematika Murni dan Aplikasi The Asian Journal of Technology Management (AJTM) JURNAL NASIONAL TEKNIK ELEKTRO ZERO : Jurnal Sains, Matematika dan Terapan INTEGER: Journal of Information Technology JMPM: Jurnal Matematika dan Pendidikan Matematika JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Jurnal Pengabdian Masyarakat Asia Jurnal Riset Mahasiswa Matematika
Vivi Aida Fitria
Unknown Affiliation
Arts Humanities Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Mathematics Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Inexact Generalized Gauss--Newton--CG for Binary Cross-Entropy Minimization Jamhuri, Mohammad; Sari, Silvi Puspita; Amiroch, Siti; Juhari, Juhari; Fitria, Vivi Aida
Jurnal Riset Mahasiswa Matematika Vol 5, No 2 (2025): Jurnal Riset Mahasiswa Matematika
Publisher : Universitas Islam Negeri Maulana Malik Ibrahim Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18860/jrmm.v5i2.34739

Abstract

Binary cross-entropy (BCE) minimization is a standard objective in probabilistic binary classification, yet practical training pipelines often rely on first-order methods whose performance can be sensitive to step-size choices and may require many iterations to reach low-loss solutions. This paper studies an inexact curvature-based solver that combines a (generalized) Gauss–Newton approximation with conjugate gradient (CG) inner iterations for minimizing the regularized BCE objective in full-batch logistic regression. At each outer iteration, the method computes a descent direction by approximately solving a damped Gauss–Newton system in a matrix-free manner via repeated products with X and X⊤, and terminates CG according to a relative-residual inexactness rule. Numerical experiments on three benchmark datasets show that the proposed Inexact GGN–CG can substantially reduce the number of outer iterations on smaller numerical data, while remaining competitive in predictive performance, and can improve both validation and test mean BCE on larger mixed-type data after one-hot encoding. In particular, on Adult Census Income the method achieves lower test mean BCE (0.3176 ± 0.0044) and higher F1-score (0.6623 ± 0.0066) than Adam and gradient descent under the same regularization-selection protocol, at the cost of additional CG work. These results highlight how damping and inexactness jointly govern the trade-off between curvature-solve effort, wall-clock time, and achieved BCE values in deterministic logistic-regression training.
Co-Authors A.N. Afandi Adriani Kala’lembang Afiyah, S. Nurul Afiyah, S. Nurul Aripriharta - Azwar Riza Habibi, Azwar Riza Budi Santoso Juhari Juhari, Juhari Kala'lembang, Adriani Khadiki, Mohammad Rizan Lilis Widayanti Mohammad Jamhuri Nira Rusanti Sari, Silvi Puspita Siti Amiroch, Siti Siti Nurul Afiyah Suastika Yulia Riska Sulistyo, Danang Arbian Titania Dwi Andini Yudistira Arya Sapoetra Zahratul Laily Binti Edaris