Federated Dynamical Low-Rank Training with Global Loss Convergence Guarantees.

Steffen Schotthöfer M. Paul Laiu

Published in: CoRR (2024)

Keyphrases

low rank
matrix factorization
linear combination
convex optimization
matrix completion
singular value decomposition
missing data
low rank matrix

rank minimization
semi supervised
trace norm
kernel matrix
high dimensional data
high order
low rank matrices
matrix decomposition

stochastic gradient descent
robust principal component analysis
training set
singular values
training samples
minimization problems
non rigid structure from motion

training data
neural network
convergence rate
principal component analysis
least squares
small number
high dimensional