A preference-based model-reduction learner with attention and set-cover pruning predicts which reduced MILP to solve, reporting faster online solving than Gurobi on benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fast and Interpretable Mixed-Integer Linear Program Solving by Learning Model Reduction
A preference-based model-reduction learner with attention and set-cover pruning predicts which reduced MILP to solve, reporting faster online solving than Gurobi on benchmarks.