Abstract: In this paper, we aim at reducing the variance of doubly stochastic optimization, a type of stochastic optimization algorithm that contains two independent sources of randomness: The subsampling of training data and the Monte Carlo estimation of expectations. Such an optimization regime often has the issue of large gradient variance which would lead to a slow rate of convergence. Therefore we propose Dual Control Variate, a new type of control variate capable of reducing gradient variance from both sources jointly. The dual control variate is built upon approximation-based control variates and incremental gradient methods. We show that on black-box variational inference, which can be formulated as a doubly stochastic optimization problem, compared with past variance reduction approaches that take only one source of randomness into account, dual control variate leads to a gradient estimator of significantly smaller variance and demonstrates significantly faster convergence.