Stochastic Forward-Douglas-Rachford Splitting for Monotone Inclusions

We propose a stochastic Forward-Douglas-Rachford Splitting framework for finding a zero point of the sum of three maximally monotone operators in real separable Hilbert space, where one of the operators is cocoercive. We characterize the rate of convergence in expectation in the case of strongly monotone operators. We provide guidance on step-size sequences that achieve this rate, even if the strong convexity parameter is unknown.

Related material