A reward-guided discrete diffusion model generates near-optimal product assortments from offline choice data without assuming a parametric choice model.
Naval Research Logistics (NRL) , volume=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diffusion-Based Data-Driven Assortment Optimization
A reward-guided discrete diffusion model generates near-optimal product assortments from offline choice data without assuming a parametric choice model.