arXiv stat.ML
· Papers
SSPO: Structure-Aware Similarity-Weighted Preference Optimization for Neural Combinatorial Optimization
arXiv:2608.12443v1 Announce Type: new Abstract: Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group. Preference-optimization methods anchor on the single best solution and discard