Inverse Multiobjective Optimization Through Online Learning
This work addresses the challenge of inferring decision-maker preferences from imperfect data, which is incremental as it builds on existing inverse optimization methods.
The paper tackles the problem of learning objective functions or constraints in multiobjective decision-making models from noisy sequential decisions, proposing an online learning framework with two algorithms that achieve high accuracy and robustness to noise.
We study the problem of learning the objective functions or constraints of a multiobjective decision making model, based on a set of sequentially arrived decisions. In particular, these decisions might not be exact and possibly carry measurement noise or are generated with the bounded rationality of decision makers. In this paper, we propose a general online learning framework to deal with this learning problem using inverse multiobjective optimization. More precisely, we develop two online learning algorithms with implicit update rules which can handle noisy data. Numerical results show that both algorithms can learn the parameters with great accuracy and are robust to noise.