A new dual spectral projected gradient method for log-determinant semidefinite programming with hidden clustering structures

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Namchaisiri, Charles, Liu, Tianxiang, Yamashita, Makoto
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909226678353920
author Namchaisiri, Charles
Liu, Tianxiang
Yamashita, Makoto
author_facet Namchaisiri, Charles
Liu, Tianxiang
Yamashita, Makoto
contents In this paper, we propose a new efficient method for a sparse Gaussian graphical model with hidden clustering structures by extending a dual spectral projected gradient (DSPG) method proposed by Nakagaki et al.~(2020). We establish the global convergence of the proposed method to an optimal solution, and we show that the projection onto the feasible region can be solved with a low computational complexity by the use of the pool-adjacent-violators algorithm. Numerical experiments on synthesis data and real data demonstrate the efficiency of the proposed method. The proposed method takes 0.91 seconds to achieve a similar solution to the direct application of the DSPG method which takes 4361 seconds.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18284
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A new dual spectral projected gradient method for log-determinant semidefinite programming with hidden clustering structures
Namchaisiri, Charles
Liu, Tianxiang
Yamashita, Makoto
Optimization and Control
90C22, 90C25, 90C26
In this paper, we propose a new efficient method for a sparse Gaussian graphical model with hidden clustering structures by extending a dual spectral projected gradient (DSPG) method proposed by Nakagaki et al.~(2020). We establish the global convergence of the proposed method to an optimal solution, and we show that the projection onto the feasible region can be solved with a low computational complexity by the use of the pool-adjacent-violators algorithm. Numerical experiments on synthesis data and real data demonstrate the efficiency of the proposed method. The proposed method takes 0.91 seconds to achieve a similar solution to the direct application of the DSPG method which takes 4361 seconds.
title A new dual spectral projected gradient method for log-determinant semidefinite programming with hidden clustering structures
topic Optimization and Control
90C22, 90C25, 90C26
url https://arxiv.org/abs/2403.18284