DOGE-Train: Discrete Optimization on GPU with End-to-end Training. (arXiv:2205.11638v1 [cs.LG])

We present a fast, scalable, data-driven approach for solving linear
relaxations of 0-1 integer linear programs using a graph neural network. Our
solver is based on the Lagrange decomposition based algorithm FastDOG (Abbas et
al. (2022)). We make the algorithm differentiable and perform backpropagation
through the dual update scheme for end-to-end training of its algorithmic
parameters. This allows to preserve the algorithm's theoretical properties
including feasibility and guaranteed non-decrease in the lower bound. Since
FastDOG can get stuck in suboptimal …

arxiv gpu optimization training