arXiv stat.ML
· Papers
Diversified Multinomial Logit Contextual Bandits
arXiv:2607.11684v1 Announce Type: new Abstract: Existing contextual multinomial logit (MNL) bandits model relevance-driven choice but ignore the potential benefits of within-assortment diversity, while submodular/combinatorial bandits encode diversity in rewards but lack structured choice probabilities. We bridge this