Lifted samplers' asymptotic variance is bounded above by twice the base algorithm's variance in a general framework covering Metropolis-Hastings, reversible jump, and similar methods.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.CO 1years
2024 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Theoretical guarantees for lifted samplers
Lifted samplers' asymptotic variance is bounded above by twice the base algorithm's variance in a general framework covering Metropolis-Hastings, reversible jump, and similar methods.