Corpus ID: 3661007

Decomposition Strategies for Constructive Preference Elicitation

  title={Decomposition Strategies for Constructive Preference Elicitation},
  author={Paolo Dragone and Stefano Teso and Mohit Kumar and Andrea Passerini},
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 itera tively by interacting with the user. Previous work has shown that Coactive Learning is a suitable method for learning user preferences in… Expand
Gradient-based Optimization for Bayesian Preference Elicitation
This work introduces a continuous formulation of EVOI as a differentiable network that can be optimized using gradient methods available in modern machine learning computational frameworks (e.g., TensorFlow, PyTorch). Expand
On the equivalence of optimal recommendation sets and myopically optimal query sets
Two different models of preference uncertainty and optimization are considered: a Bayesian framework in which a posterior over user utility functions is maintained, optimal recommendations are assessed using expected utility, and queries are assessed using expected value of information and a minimax-regret framework, in which user utility uncertainty is strict. Expand
Automating Layout Synthesis with Constructive Preference Elicitation
This work proposes addressing layout synthesis by casting it as a constructive preference elicitation task, and employs a coactive interaction protocol, whereby the system and the designer interact by mutually improving each other’s proposals. Expand
No more ready-made deals: constructive recommendation for telco service bundling
A new recommendation system for service and product bundling in the domain of telecommunication and multimedia, which exploits the recent constructive preference elicitation framework to be highly usable with respect to both time and number of interactions. Expand
Pyconstruct: Constraint Programming Meets Structured Prediction
Pyconstruct is introduced, a Python library tailored for solving real-world constructive problems with minimal effort that leverages max-margin approaches to decouple learning from synthesis and constraint programming as a generic framework for synthesis. Expand


Constraint-based optimization and utility elicitation using the minimax decision criterion
This work proposes the use of minimax regret as a suitable decision criterion for decision making in the presence of such utility function uncertainty, and proposes various elicitation methods that can be used to refine utility uncertainty in such a way as to quickly reduce minimax regrets. Expand
Making Rational Decisions Using Adaptive Utility Elicitation
An algorithm is proposed that interleaves the analysis of the decision problem and utility elicitation to allow these two tasks to inform each other and computes the best strategy based on the information acquired so far. Expand
Constructive Preference Elicitation by Setwise Max-Margin Learning
The setwise max- margin method can be viewed as a generalization of max-margin learning to sets, and can produce a set of "diverse" items that can be used to ask informative queries to the user. Expand
Coactive Critiquing: Elicitation of Preferences and Features
This paper extends Coactive Learning, which iteratively collects manipulative feedback, to optionally query example critiques, and presents an upper bound on the average regret suffered by the learner. Expand
Coactive Learning for Locally Optimal Problem Solving
The study of coactive learning is extended to problems where obtaining a globally optimal or near-optimal solution may be intractable or where an expert can only be expected to make small, local improvements to a candidate solution. Expand
Local Utility Elicitation in GAI Models
This work proposes a procedure to elicit GAI model parameters using only "local" utility queries rather than "global" queries over full outcomes, which takes full advantage of GAI structure and provides a sound framework for extending the elicitation procedure to settings where the uncertainty over utility parameters is represented probabilistically. Expand
Preferences in artificial intelligence
A focused survey about the presence and the use of the concept of “preferences” in Artificial Intelligence, which essentially covers the basics of preference modelling, theUse of preference in reasoning and argumentation, the problem of compact representations of preferences, preference learning and theuse of non conventional preference models based on extended logical languages. Expand
Coactive Learning
It is shown that it is possible to adapt many existing online learning algorithms to the coactive framework and provide algorithms that achieve O(1/√T) average regret in terms of cardinal utility, even though the learning algorithm never observes cardinal utility values directly. Expand
Elicitation of Factored Utilities
It is argued for the importance of assessing numerical utilities rather than qualitative preferences, and several utility elicitation techniques from artificial intelligence, operations research, and conjoint analysis are surveyed. Expand
Finite-time Analysis of the Multiarmed Bandit Problem
This work shows that the optimal logarithmic regret is also achievable uniformly over time, with simple and efficient policies, and for all reward distributions with bounded support. Expand