SNMPBB adapts nonmonotone projected Barzilai-Borwein methods to symmetric NMF, proving convergence and demonstrating 6x speedups over SymANLS on synthetic data plus competitive or better results on real clustering benchmarks and large matrices.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Nonmonotone Gradient-Based Algorithm for Symmetric Nonnegative Matrix Factorization and Graph Clustering
SNMPBB adapts nonmonotone projected Barzilai-Borwein methods to symmetric NMF, proving convergence and demonstrating 6x speedups over SymANLS on synthetic data plus competitive or better results on real clustering benchmarks and large matrices.