Large scale optimization problems arise in diverse fields. Decomposing the large scale problem into small scale subproblems regarding the variable interactions and optimizing them cooperatively are critical steps in an optimization algorithm. To explore the variable interactions and perform the problem decomposition tasks, we develop a two stage variable interaction reconstruction algorithm. A learning model is proposed to explore part of the variable interactions as prior knowledge. A marginalized denoising model is proposed to construct the overall variable interactions using the prior knowledge, with which the problem is decomposed into small scale modules. To optimize the subproblems and relieve premature convergence, we propose a cooperative hierarchical particle swarm optimization framework, where the operators of contingency leadership, interactional cognition, and self-directed exploitation are designed. Finally, we conduct theoretical analysis for further understanding of the proposed algorithm. The analysis shows that the proposed algorithm can guarantee converging to the global optimal solutions if the problems are correctly decomposed. Experiments are conducted on the CEC2008 and CEC2010 benchmarks. The results demonstrate the effectiveness, convergence, and usefulness of the proposed algorithm.