PoolDFL: Solver-Free Decision-Focused Learning with Augmented Solution Pools

Decision-focused learning often requires solving an optimisation problem at every training step. We introduce PoolDFL, which augments a shared pool of training optima with feasible neighbours and keeps the pool fixed throughout training. Neighbour enumeration requires no additional solver calls, and each update evaluates a restricted SPO+ loss through matrix products and maximisation over the pool. This loss recovers the full objective whenever the pool contains a global optimum of its inner optimisation problem. Experiments on shortest path, assignment and knapsack show that augmentation improves decision quality over pools containing only training optima. On $10\times 10$ shortest path, PoolDFL has a mean regret gap of $-0.02\%$ relative to SPO+ over 35 paired seeds. On assignment, it satisfies a $1\%$ non-inferiority criterion after Holm correction. Gradient diagnostics associate closer alignment with the full objective with smaller regret gaps.