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

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

arXiv机器学习 2026-11-13 22:49 8 阅读 查看原文
用户需要我把一段纯文本的新闻正文(实际上是一段学术论文摘要)排版成语义化的HTML片段。规则如下: 1. 只输出HTML片段本身,不要Markdown围栏,不要解释。 2. 每个自然段落用`

`包裹,长文用`

`/`

`划分小节。 3. 列表用`
  • `,引用用`
    `,代码用`
    `,重要句子可用``。
    4. 保留原文所有信息,不得增删改内容。
    5. 不要输出``、``、``等文档级标签。
    
    原文:
    "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 $ε$-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."
    
    这是一段非常长的摘要,可以分成几个自然段,或者加个标题。由于它没有明显的小节标题,我可以把它分成几个段落,或者加一个`

    `作为大标题,然后分成几个`

    `。 比如:

    Preference-Guided Multi-Objective Optimization

    (但是不能增删改内容!规则4:保留原文所有信息,不得增删改内容。所以不能自己加标题!) 那直接分段。原文其实是一整段。如果必须分段,可以按句群分段,但不能增加内容。 或者整个作为一段 `

    `。 规则2说“每个自然段落用`

    `包裹,长文用`

    `/`

    `划分小节”。这里没有小节,所以直接用`

    `包裹整个文本,或者按逻辑拆成几个`

    `。 比如拆成三段: 第一段:方法提出(Learning across... single objective.) 第二段:算法与理论(We further develop... prior works.) 第三段:实验与代码(Experiments on... https://github.com/tpgoodboy/ParetoM3.) 检查原文是否有可以加粗的重要句子。 "we propose a penalty-based min-max-min formulation, termed the M$^3$ problem" -> 可以加粗。 "We further develop ParetoM$^3$, a single-loop first-order algorithm" -> 可以加粗。 "we prove that ParetoM$^3$ finds an $ε$-stationary point" -> 可以加粗。 不过,为了严格遵守“不得增删改内容”,加粗只是HTML标签,不改变文本内容,是允许的。 关于数学符号,原文是 `M$^3$` 和 `$ε$-stationary`。我需要保留这些符号,或者在HTML中直接保留 `M$^3$` 和 `$ε$`。 分段处理:

    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 $ε$-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

    等等,URL用 `
    ` 包裹合适吗?规则3说“代码用`
    `”。URL算代码吗?可以用 `https://github.com/tpgoodboy/ParetoM3` 更合适。
    
    再检查规则:
    1. 只输出HTML片段本身,不要Markdown围栏、不要解释; -> 好的。
    2. 每个自然段落用`

    `包裹,长文用`

    `/`

    `划分小节; -> 没有小节,直接用`

    `。 3. 列表内容用`

    • `,引用用`
      `,代码用`
      `,重要句子可用``; -> 使用了``和``。
      4. 保留原文所有信息,不得增删改内容; -> 文本完全一致。
      5. 不要输出``/``/``等文档级标签。 -> 好的。
      
      微调加粗:
      

      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 $ε$-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.

      注意原文最后是 "Code is available at https://github.com/tpgoodboy/ParetoM3." 有个句号。 用 `https://github.com/tpgoodboy/ParetoM3