An Online-Learning Approach to Inverse Optimization
Reviewed by Pithpith:2TI7N45Zopen to challenge →
read the original abstract
In this paper, we demonstrate how to learn the objective function of a decision-maker while only observing the problem input data and the decision-maker's corresponding decisions over multiple rounds. We present exact algorithms for this online version of inverse optimization which converge at a rate of $ \mathcal{O}(1/\sqrt{T}) $ in the number of observations~$T$ and compare their further properties. Especially, they all allow taking decisions which are essentially as good as those of the observed decision-maker already after relatively few iterations, but are suited best for different settings each. Our approach is based on online learning and works for linear objectives over arbitrary feasible sets for which we have a linear optimization oracle. As such, it generalizes previous approaches based on KKT-system decomposition and dualization. We also introduce several generalizations, such as the approximate learning of non-linear objective functions, dynamically changing as well as parameterized objectives and the case of suboptimal observed decisions. When applied to the stochastic offline case, our algorithms are able to give guarantees on the quality of the learned objectives in expectation. Finally, we show the effectiveness and possible applications of our methods in indicative computational experiments.
This paper has not been read by Pith yet.
Forward citations
Cited by 1 Pith paper
-
Finite and Corruption-Robust Regret Bounds in Online Inverse Linear Optimization under M-Convex Action Sets
Finite O(d log d) regret bounds for online inverse linear optimization under M-convex action sets, plus O((C+1)d log d) corruption-robust bounds without knowing C.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.