A tutorial on learning from preferences and choices with Gaussian Processes

arXiv stat.ML / 5/5/2026

💬 OpinionIdeas & Deep AnalysisModels & Research

共有:

Key Points

The tutorial proposes an integrated framework for preference learning using Gaussian Processes, linking economics/decision theory concepts of rationality with GP-based machine learning.
It shows how customizing the likelihood function can yield preference models covering random utility models, bounded rationality (limits of discernment), and cases with multiple conflicting utilities.
The framework is designed to handle both object-preferences and label-preferences, extending GP preference modeling across different preference representation settings.
It builds on existing research while also introducing new GP-based models to address gaps in the current literature.
The work aims to support more personalized and expectation-aligned product and application behavior by learning individuals’ preferences more effectively.

Abstract

Preference modelling lies at the intersection of economics, decision theory, machine learning and statistics. By understanding individuals' preferences and how they make choices, we can build products that closely match their expectations, paving the way for more efficient and personalised applications across a wide range of domains. The objective of this tutorial is to present a cohesive and comprehensive framework for preference learning with Gaussian Processes (GPs), demonstrating how to seamlessly incorporate rationality principles (from economics and decision theory) into the learning process. By suitably tailoring the likelihood function, this framework enables the construction of preference learning models that encompass random utility models, limits of discernment, and scenarios with multiple conflicting utilities for both object- and label-preference. This tutorial builds upon established research while simultaneously introducing some novel GP-based models to address specific gaps in the existing literature.