Data-Driven Preference Sampling for Pareto Front Learning

arXiv:2404.08397v1 Announce Type: new
Abstract: Pareto front learning is a technique that introduces preference vectors in a neural network to approximate the Pareto front. Previous Pareto front learning methods have demonstrated high performance in approximating simple Pareto fronts. These methods often sample preference vectors from a fixed Dirichlet distribution. However, no fixed sampling distribution can be adapted to diverse Pareto fronts. Efficiently sampling preference vectors and accurately estimating the Pareto front is a challenge. To address this challenge, we propose …

abstract arxiv cs.lg data data-driven distribution however network neural network pareto performance sample sampling simple type vectors