Variational Bayesian methods approximate intractable integrals found in Bayesian inference and machine learning. Primarily, these methods serve one of two purposes: Approximating the posterior distribution, or bounding the marginal likelihood of observed data.
Variational Bayesian methods provide a locally optimal, exactly analytical solution to intractable integrals in Bayesian inference and machine learning. They are often presented as a faster, approximate alternative to MCMC methods of posterior inference.
