Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules
We learn schedules for a continuous penalty relaxation of MAX-CUT by backpropagating through an unrolled classical solver. A state-blind schedule generalizes to instances substantially larger than those used for training. A state-adaptive bilinear schedule also generalizes out of distribution, outperforming its untrained baseline across 15 seeds ($t=4.1$). By contrast, an additive ablation with…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
