Transformer-based Stagewise Decomposition Algorithm for Efficient Solving of Large-Scale Multistage Stochastic Optimization Problems

The authors propose TranSDDP, a novel Transformer-based stagewise decomposition algorithm, to efficiently generate piecewise linear approximations of the value function and solve large-scale multistage stochastic optimization problems. The TranSDDP model leverages the structural advantages of the Transformer architecture to integrate subgradient cutting planes, significantly reducing computation time while preserving solution quality.