Approximate inference methods make it possible to learn realistic models from big data by trading off computation time for accuracy, when exact learning and inference are computationally intractable.

Major methods classes

• Laplace's approximation
• Variational Bayesian methods
• Markov chain Monte Carlo
• Expectation propagation
• Markov random fields
• Bayesian networks
  • Variational message passing
• Loopy and generalized belief propagation

^[1][2]