A Proximal Gradient Framework for Composite Multiobjective Optimization on Riemannian Manifolds

Abstract

This paper proposes a Riemannian Multiobjective Proximal Gradient Method (RMPGM) for composite optimization problems on manifolds. Unlike scalarization-based approaches, the proposed framework directly handles vector-valued objectives and establishes global convergence to Pareto stationary points, together with an $\mathcal{O}(1/k)$ convergence rate. We further develop two variants to enhance practicality and performance: an inexact RMPGM that allows controlled inexactness in solving subproblems, and a trust-region RMPGM that adaptively adjusts the penalty parameter and achieves an $\mathcal{O}(\hat{I}{\mu }^{-2})$iteration complexity. Numerical experiments demonstrate that the proposed methods are consistently outperform subgradient-based baselines.