A latent-variable hypothesis class lets inverse optimization recover feasible regions for known linear objectives, with convex and MILP training reformulations in special cases.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Inverse Optimization via Learning Feasible Regions
A latent-variable hypothesis class lets inverse optimization recover feasible regions for known linear objectives, with convex and MILP training reformulations in special cases.