SLMC generalizes random-coordinate and preconditioned Langevin Monte Carlo by projecting updates onto random eigenblocks of a preconditioner, with coupling-based error bounds.
Efficientgradient flows in sliced-Wasserstein space.Transactions on Machine Learning Research, 2022
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Subspace Langevin Monte Carlo
SLMC generalizes random-coordinate and preconditioned Langevin Monte Carlo by projecting updates onto random eigenblocks of a preconditioner, with coupling-based error bounds.