Learning to optimize by multi-gradient for multi-objective optimization

doi:10.1007/s11425-023-2392-8

Return

Learning to optimize by multi-gradient for multi-objective optimization

2025-11-01

PRE

Xinmin Yang

汤历平 (Liping Tang) *

DOI：10.1007/s11425-023-2392-8

Original

Original request for help

Save

Abstract

En 中文

The development of artificial intelligence for science has led to the emergence of learning-based research paradigms, necessitating a compelling reevaluation of the design of multi-objective optimization (MOO) methods. The new generation MOO methods should be rooted in automated learning rather than manual design. In this paper, we introduce a new automatic learning paradigm for optimizing MOO problems, and propose a multi-gradient learning to optimize (ML2O) method, which automatically learns a generator (or mappings) from multiple gradients to update directions. As a learning-based method, ML2O acquires knowledge of local landscapes by leveraging information from the current step and incorporates global experience extracted from historical iteration trajectory data. By introducing a new guarding mechanism, we propose a guarded multi-gradient learning to optimize (GML2O) method, and prove that the iterative sequence generated by GML2O converges to a Pareto stationary point. The experimental results demonstrate that our learned optimizer outperforms hand-designed competitors on training the multi-task learning neural network.

Keywords:

multi-objective optimization

learning to optimize

stochastic gradient method

safeguard