Back to AI News
arxiv

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.

AI Brief

Provides a novel algorithm with theoretical guarantees for a practical multi-objective optimization problem, backed by experiments and released code.

arXiv:2611.18252v1 Announce Type: cross Abstract: Learning across multiple inherently conflicting objectives requires selecting desirable trade-offs from the Pareto set. In this work, we study preference-guided multi-objective optimization, where a predefined preference function is minimized over the weak Pareto set of multiple nonconvex objectives. Leveraging a merit function that vanishes on the weak Pareto set, we propose a penalty-based min-max-min formulation, termed the M$^3$ problem, which unifies preference optimization and the enforcement of weak Pareto optimality in a single objective. We further develop ParetoM$^3$, a single-loop first-order algorithm for computing stationary solutions of the resulting M$^3$ problem. Under a local Kurdyka-Lojasiewicz assumption, we prove that ParetoM$^3$ finds an $\epsilon$-stationary point of the M$^3$ problem that is also approximately weakly Pareto optimal for the original multi-objective problem when the penalty parameter is sufficiently large, with explicit non-asymptotic convergence rates. We also show that this stationarity notion recovers existing optimality criteria, including approximate preference stationarity and approximate Karush-Kuhn-Tucker conditions, under the same assumptions used in prior works. Experiments on a synthetic benchmark, image classification, regression, and math reasoning demonstrate that ParetoM$^3$ reliably attains preferred weak Pareto optimal solutions while achieving strong practical performance. Code is available at https://github.com/tpgoodboy/ParetoM3.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!