Preference elicitation for interactive learning of Optimization Modulo Theory problems
نویسندگان
چکیده
We consider the problem of automatically discovering the solution preferred by a decision maker (DM). Recent work in the field of constraint programming [8] formalizes the user preferences in terms of soft constraints, whose weights are assumed to be partially unknown. An elicitation strategy is introduced based on the DM queries for constraint weights. In this paper, soft constraints are cast into weighted Boolean terms. The DM preference is represented by a combinatorial utility function which is a weighted combination of Boolean terms. The optimization task is translated into a weighted Maximum Satisfiability (MAX-SAT) problem where the objective function is unknown and has to be interactively learnt.
منابع مشابه
Learning Modulo Theories for preference elicitation in hybrid domains
This paper introduces CLEO, a novel preference elicitation algorithm capable of recommending complex objects in hybrid domains, characterized by both discrete and continuous attributes and constraints defined over them. The algorithm assumes minimal initial information, i.e., a set of catalog attributes, and defines decisional features as logic formulae combining Boolean and algebraic constrain...
متن کاملLearning to diversify in complex interactive Multiobjective Optimization
Many real-world problems have a natural formulation as Multiobjective Optimization Problems (MOPs), in which multiple conflicting objectives need to be simultaneously optimized. A popular approach to deal with the resulting complexity consists of interacting with the Decision Maker (DM) during optimization, progressively focusing towards her preferred area in the decision space. In BC-EMO, an e...
متن کاملDecomposition Strategies for Constructive Preference Elicitation
We tackle the problem of constructive preference elicitation, that is the problem of learning user preferences over very large decision problems, involving a combinatorial space of possible outcomes. In this setting, the suggested configuration is synthesized on-the-fly by solving a constrained optimization problem, while the preferences are learned iteratively by interacting with the user. Pre...
متن کاملInteractive Decomposition Multi-Objective Optimization via Progressively Learned Value Functions
Decomposition has become an increasingly popular technique for evolutionary multiobjective optimization (EMO). A decomposition-based EMO algorithm is usually designed to approximate a whole Pareto-optimal front (PF). However, in practice, the decision maker (DM) might only be interested in her/his region of interest (ROI), i.e., a part of the PF. Solutions outside that might be useless or even ...
متن کاملForm + Function: Optimizing Aesthetic Product Design via Adaptive, Geometrized Preference Elicitation
Visual design is critical to product success, and the subject of intensive marketing research effort. Yet visual elements, due to their high‐dimensional, holistic, and interactive nature, do not lend themselves well to optimization using extant methods for preference elicitation. Here we present a systematic methodology to incorporate real‐time, interactive, 3D‐rendered product configurations i...
متن کامل