Flexible variational distributions improve variational inference but are harder to optimize. In this work we present a control variate that is applicable for any reparameterizable distribution with known mean and covariance matrix, e.g. Gaussians with any covariance structure. The control variate is based on a quadratic approximation of the model, and its parameters are set using a double-descent scheme by minimizing the gradient estimator's variance. We empirically show that this control variate leads to large improvements in gradient variance and optimization convergence for inference with non-factorized variational distributions.

翻译：灵活可变分布会改善变异推论, 但更难优化 。 在这项工作中, 我们提出了一个控制变量, 适用于任何已知平均和共变矩阵的可重新校准分布, 如具有任何共变结构的高斯。 控制变量以模型的四面形近似为基础, 其参数是使用双白法设定的, 以最小化梯度估量器的差价 。 我们从经验上表明, 这种控制变量导致梯度差异和优化趋同于非因子变异分布的推论, 从而大大改善梯度差异和优化趋同 。