Exact Manifold Gaussian Variational Bayes. (arXiv:2210.14598v1 [stat.ML])

We propose an optimization algorithm for Variational Inference (VI) in
complex models. Our approach relies on natural gradient updates where the
variational space is a Riemann manifold. We develop an efficient algorithm for
Gaussian Variational Inference that implicitly satisfies the positive definite
constraint on the variational covariance matrix. Our Exact manifold Gaussian
Variational Bayes (EMGVB) provides exact but simple update rules and is
straightforward to implement. Due to its black-box nature, EMGVB stands as a
ready-to-use solution for VI in …

arxiv bayes manifold