PMGDA: A Preference-based Multiple Gradient Descent Algorithm

arXiv:2402.09492v1 Announce Type: new
Abstract: It is desirable in many multi-objective machine learning applications, such as multi-task learning and multi-objective reinforcement learning, to find a Pareto optimal solution that can exactly match a given preference of decision-makers. 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 the exact Pareto optimal solutions required by a decision maker. …

abstract algorithm applications arxiv cs.lg decision gradient information machine machine learning machine learning applications makers match multi-objective multiple multi-task learning pareto reinforcement reinforcement learning scale solution type