跳到正文
arXiv cs.AI· Pei Tang, Songtao Lu·· 4 小时前AI 评分38

ParetoM³:基于 min-max-min 优化的偏好引导 Pareto 集学习

ParetoM$^3$: Learning on the Pareto Set under Preference Guidance via Min-Max-Min Optimization

AI 导读

arXiv 论文提出 ParetoM³,一种单循环一阶算法,用于求解偏好引导下的多目标优化 min-max-min(M³)问题,在弱 Pareto 集上最小化预设偏好函数。

正文 · 原文

View PDF HTML (experimental)

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 this https URL.
Comments: Accepted at the 40th Annual Conference on Neural Information Processing Systems (NeurIPS 2026)
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Optimization and Control (math.OC)
Cite as: arXiv:2611.18252 [cs.LG]
  (or arXiv:2611.18252v1 [cs.LG] for this version)
  https://doi.org/10.48550/arXiv.2611.18252

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Songtao Lu [view email]
[v1] Fri, 13 Nov 2026 14:49:23 UTC (389 KB)

来源:arXiv cs.AI · arxiv.org