SpectralUnmix: A Torch-Based Regularized Non-negative Matrix Factorization

Abstract

We present SpectralUnmix, an R package for regularized non-negative matrix factorization (NMF), implemented in torch with optional GPU acceleration. The package estimates low-rank non-negative representations through proximal-gradient updates and allows smoothness regularization along the spectral axis. As a compact demonstration, we apply the method to a subset of stellar spectra and compare the recovered NMF components with principal-component directions and representative stellar spectra. The package is released under the MIT license at \href{https://rafaelsdesouza.github.io/SpectralUnmix/}{this repository}.

Accepted in Research Notes of AAS

References in corpus (9)

• K-corrections and filter transformations in the ultraviolet, optical, and near infrared
• A new library of theoretical stellar spectra with scaled-solar and alpha-enhanced mixtures
• SCARLET: Source separation in multi-band images by Constrained Matrix Factorization
• PCA Tomography: how to extract information from datacubes
• Kernel PCA for type Ia supernovae photometric classification
• A PCA-based automated finder for galaxy-scale strong lenses
• Robust PCA and MIC statistics of baryons in early mini-haloes
• Learning the Fundamental MIR Spectral Components of Galaxies with Non-Negative Matrix Factorisation
• qrpca: A Package for Fast Principal Component Analysis with GPU Acceleration