BriefGPT.xyz
Sep, 2023
基于调优自由的最小体积非负矩阵分解研究
Towards Tuning-Free Minimum-Volume Nonnegative Matrix Factorization
HTML
PDF
Duc Toan Nguyen, Eric C. Chi
TL;DR
用最小体积非负矩阵分解方法，不依赖噪声水平来可恢复秩缺失的矩阵，并通过无需调整的平方根 lasso 方法来选择调整参数值。
Abstract
nonnegative matrix factorization
(NMF) is a versatile and powerful tool for discovering
latent structures
in data matrices, with many variations proposed in the literature. Recently, Leplat et al.\@ (2019) introd
→