Let's assume that we are doing approximate Bayesian inference and compute the convergence of our posterior estimate to the true value of the parameter using Wasserstein distance. Why posterior convergence in expectation is stronger than posterior convergence in probability?

  • $\begingroup$ Could you be more specific, especially concerning what you mean by "posterior convergence"? That phrase sounds like it could apply to almost any iterative numerical algorithm. $\endgroup$ – whuber May 16 at 17:10

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.