Novel PDMPs using mirror maps enable unbiased sampling from distributions on convex sets while allowing exact subsampling and outperforming SDE methods.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Deterministic envelopes decouple stochastic-gradient noise from taming in SGLD, splitting stationary error into oracle-dependent bias and deterministic stabilization error, with a hybrid soft-hard design for far tails.
citing papers explorer
-
Piecewise Deterministic Sampling for Constrained Distributions
Novel PDMPs using mirror maps enable unbiased sampling from distributions on convex sets while allowing exact subsampling and outperforming SDE methods.
-
Deterministic Envelopes for Tamed SGLD: Decoupling Stochastic-Gradient Noise and Localizing Taming
Deterministic envelopes decouple stochastic-gradient noise from taming in SGLD, splitting stationary error into oracle-dependent bias and deterministic stabilization error, with a hybrid soft-hard design for far tails.