AI RESEARCH

Adaptive Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Learning

arXiv CS.AI

ArXi:2410.21764v3 Announce Type: replace-cross Multi-objective learning (MOL) aims to learn under multiple potentially conflicting objectives and strike a proper balance. While recent preference-guided MOL methods often rely on additional optimization objectives or constraints, we consider the classic Tchebycheff scalarization (TCH) that naturally allows for locating solutions with user-specified trade-offs. Due to its minimax formulation, directly optimizing TCH often leads to