Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold

Optimization in the Bures-Wasserstein space has been gaining popularity in the machine learning community since it draws connections between variational inference and Wasserstein gradient flows. The variational inference objective function of Kullback-Leibler divergence can be written as the sum of the negative entropy and the potential energy, making forward-backward Euler the method of choice. Notably, the backward step admits a closed-form solution in this case, facilitating the practicality of the scheme. However, the forward step is not exact since the Bures-Wasserstein gradient of the potential energy involves "intractable" expectations. Recent approaches propose using the Monte Carlo method -in practice a single-sample estimator -to approximate these terms, resulting in high variance and poor performance. We propose a novel variance-reduced estimator based on the principle of control variates. We theoretically show that this estimator has a smaller variance than the Monte-Carlo estimator in scenarios of interest. We also prove that variance reduction helps improve the optimization bounds of the current analysis. We empirically demonstrate that the proposed estimator gains order-of-magnitude improvements over previous Bures-Wasserstein methods. Recently, there has been emerging interest in Gaussian VI with a new geometric Riemannian optimization perspective (Lambert et al., 2022; Diao et al., 2023). The family of non-degenerate Gaus-