AI RESEARCH
Large Neighborhood Search meets Iterative Neural Constraint Heuristics
arXiv CS.LG
•
ArXi:2603.20801v1 Announce Type: new Neural networks are being increasingly used as heuristics for constraint satisfaction. These neural methods are often recurrent, learning to iteratively refine candidate assignments. In this work, we make explicit the connection between such iterative neural heuristics and Large Neighborhood Search (LNS), and adapt an existing neural constraint satisfaction method-ConsFormer-into an LNS procedure. We decompose the resulting neural LNS into two standard components: the destroy and repair operators.