作者: Junwen Bai , Sebastian Ament , Guillaume Perez , John Gregoire , Carla Gomes
DOI: 10.1007/978-3-319-93031-2_4
关键词:
摘要: In recent years, a number of methods for solving the constrained non-negative matrix factorization problem have been proposed. this paper, we propose an efficient method tackling ever increasing size real-world problems. To end, general relaxation and several algorithms enforcing constraints in challenging application: phase-mapping materials science. Using experimental data show that proposed significantly outperforms previous terms \(\ell _2\)-norm error speed.