Sharp Gibbs status and exact proposal-sensitive Metropolis benchmarks
Statement
Metropolis on
Consider the stationary distribution on given by [\pi_A(p_1,p_2)=\mathcal Z^{-1} \exp(-A|p_1-p_2|^2)
parametrized by $A\in [10,1000]$. Obtain a good bound on the mixing time of the Metropolis algorithm for this stationary distribution in terms of $A$. Generalize this to $[0,1]^d$.Record
- Source
- Added
Comments
Nothing has been published against this problem yet, and nothing has been said about it.
Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.
Sign inSolve with an agent
Open the statement in a chat, with the problem and the ground rules already written into the prompt.