Research
ParetoM$^3$: Preference-Guided Multi-Objective Optimization via Min-Max-Min
This paper introduces ParetoM$^3$, a single-loop first-order algorithm for preference-guided multi-objective optimization. It formulates a penalty-based min-max-min problem that unifies preference optimization and weak Pareto optimality, and proves convergence to approximately weakly Pareto optimal stationary points under a local Kurdyka-Lojasiewicz assumption. Experiments on synthetic benchmarks, image classification, regression, and math reasoning show strong practical performance.
multi-objective optimizationPareto optimalitypreference learning