Develops hierarchical Bayesian models and two MCMC algorithms for posterior inference on inverse optimization parameters, establishing consistency and demonstrating credible region coverage under identifiability conditions.
Inverse optimization via learning feasible regions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Noiseless inverse optimization admits tight high-probability O(d/T) generalization bounds on the induced action set that extend to regret and match adversarial upper bounds.
citing papers explorer
-
Uncertainty Quantification in Data-Driven Inverse Optimization via Bayesian Inference
Develops hierarchical Bayesian models and two MCMC algorithms for posterior inference on inverse optimization parameters, establishing consistency and demonstrating credible region coverage under identifiability conditions.
-
Tight Generalization Bounds for Noiseless Inverse Optimization
Noiseless inverse optimization admits tight high-probability O(d/T) generalization bounds on the induced action set that extend to regret and match adversarial upper bounds.