A0361
Title: MCMC when you do not want to evaluate the target distribution
Authors: Guanyang Wang - Rutgers University (United States) [presenting]
Wei Yuan - Rutgers University (United States)
Abstract: In sampling tasks, it is common for target distributions to be known up to a normalizing constant. However, in numerous situations, evaluating even the unnormalized distribution proves to be costly or infeasible. This issue arises in scenarios such as sampling from the Bayesian posterior for large datasets and the 'doubly intractable' distributions. The aim is to introduce a unified framework that includes various MCMC algorithms, including several minibatch MCMC algorithms and the exchange algorithm. This framework not only simplifies the theoretical analysis of existing algorithms but also leads to the development of new, more efficient algorithms.
