Proposes KIPLMC algorithms based on joint parameter-latent diffusions with nonasymptotic Wasserstein-2 rates under strong concavity, claiming improved dimension dependence over prior Langevin methods.
Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.CO 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Kinetic Interacting Particle Langevin Monte Carlo
Proposes KIPLMC algorithms based on joint parameter-latent diffusions with nonasymptotic Wasserstein-2 rates under strong concavity, claiming improved dimension dependence over prior Langevin methods.