A neural-network parametrized gradient descent method for low-rank plus sparse decomposition of covariance matrices, with a polynomial-in-dimensions convergence rate to a stationary point.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Low-Rank plus Sparse Decomposition of Covariance Matrices using Neural Network Parametrization
A neural-network parametrized gradient descent method for low-rank plus sparse decomposition of covariance matrices, with a polynomial-in-dimensions convergence rate to a stationary point.