Metric Learning to Accelerate Convergence of Operator Splitting Methods for Differentiable Parametric Programming

arXiv:2404.00882v1 Announce Type: new
Abstract: Recent work has shown a variety of ways in which machine learning can be used to accelerate the solution of constrained optimization problems. Increasing demand for real-time decision-making capabilities in applications such as artificial intelligence and optimal control has led to a variety of approaches, based on distinct strategies. This work proposes a novel approach to learning optimization, in which the underlying metric space of a proximal operator splitting algorithm is learned so as to …

abstract applications artificial artificial intelligence arxiv capabilities control convergence cs.lg decision demand differentiable intelligence machine machine learning making optimization parametric programming real-time solution type work