Gibbs sampling from log-smooth strongly log-concave targets mixes in O*(kappa^2 n^7.5 (max{1, sqrt(n^{-1} log(2M/gamma))})^2) steps from an M-warm start.
Preduce — a probabilistic algorithm identifying redundancy by a random feasible point generator (RFPG)
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
math.ST 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A mixing time bound for Gibbs sampling from log-smooth log-concave distributions
Gibbs sampling from log-smooth strongly log-concave targets mixes in O*(kappa^2 n^7.5 (max{1, sqrt(n^{-1} log(2M/gamma))})^2) steps from an M-warm start.