English

PMGDA: A Preference-based Multiple Gradient Descent Algorithm

Machine Learning 2024-02-19 v2

Abstract

It is desirable in many multi-objective machine learning applications, such as multi-task learning with conflicting objectives and multi-objective reinforcement learning, to find a Pareto solution that can match a given preference of a decision maker. These problems are often large-scale with available gradient information but cannot be handled very well by the existing algorithms. To tackle this critical issue, this paper proposes a novel predict-and-correct framework for locating a Pareto solution that fits the preference of a decision maker. In the proposed framework, a constraint function is introduced in the search progress to align the solution with a user-specific preference, which can be optimized simultaneously with multiple objective functions. Experimental results show that our proposed method can efficiently find a particular Pareto solution under the demand of a decision maker for standard multiobjective benchmark, multi-task learning, and multi-objective reinforcement learning problems with more than thousands of decision variables. Code is available at: https://github.com/xzhang2523/pmgda. Our code is current provided in the pgmda.rar attached file and will be open-sourced after publication.}

Keywords

Cite

@article{arxiv.2402.09492,
  title  = {PMGDA: A Preference-based Multiple Gradient Descent Algorithm},
  author = {Xiaoyuan Zhang and Xi Lin and Qingfu Zhang},
  journal= {arXiv preprint arXiv:2402.09492},
  year   = {2024}
}