Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein Space

no code implementations • 10 Apr 2023 • Michael Diao, Krishnakumar Balasubramanian, Sinho Chewi, Adil Salim

Of key interest in statistics and machine learning is Gaussian VI, which approximates $\pi$ by minimizing the Kullback-Leibler (KL) divergence to $\pi$ over the space of Gaussians.

Variational Inference