Optimal Neural Network Approximations of Wasserstein Gradient Direction via Convex Optimization

Yifei Wang, Peng Chen, Mert Pilanci, Wuchen Li

Keywords: Bayesian inference, Wasserstein gradient descent, neural networks, convex optimization

Abstract: The computation of Wasserstein gradient direction is essential for posterior sampling problems and scientific computing. The approximation of the Wasserstein gradient with finite samples requires solving a variational problem. We study the variational problem in the family of two-layer networks with squared-ReLU activations, towards which we derive a semi-definite programming (SDP) relaxation. This SDP can be viewed as an approximation of the Wasserstein gradient in a broader function family including two-layer networks. By solving the convex SDP, we obtain the optimal approximation of the Wasserstein gradient direction in this class of functions. Numerical experiments including PDE-constrained Bayesian inference and parameter estimation in COVID-19 modeling demonstrate the effectiveness of the proposed method.

TL;DR: Propose a convex optimization problem for approximating Wasserstein gradient direction