A scenario-embedded neural network with feasibility decoder and composite loss learns to proxy solutions for sequential contextual stochastic programs, achieving 2800x speedup and cost improvements in order fulfillment simulations.
arXiv preprint arXiv:2505.17340 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Optimization Proxies for Sequential Contextual Stochastic Programs: An Order Fulfillment Application
A scenario-embedded neural network with feasibility decoder and composite loss learns to proxy solutions for sequential contextual stochastic programs, achieving 2800x speedup and cost improvements in order fulfillment simulations.