高维多目标学习中，正则化能帮上忙吗？
Learning Pareto manifolds in high dimensions: How can regularization help?
- 提出两阶段框架，利用数据低维结构提升多目标学习效果
- 在多分布学习和公平性-风险权衡任务中验证有效
- 揭示了传统正则化在多目标场景下的失效机制
现代机器学习越来越需要同时优化多个目标。然而，数据通常高维且标注成本高昂。对于单一目标（如预测风险），已知当数据具有低维结构（如稀疏性）时，常规正则化可提升泛化能力。但多目标学习（MOL）中如何利用此类结构仍不明确。本文分析了直接应用传统正则化方法的失败原因，并提出一个两阶段MOL框架，可有效利用低维结构。实验表明该框架在多分布学习和公平性-风险权衡任务中表现优异。
原文摘要 · Abstract (English)
Simultaneously addressing multiple objectives is becoming increasingly important in modern machine learning. At the same time, data is often high-dimensional and costly to label. For a single objective such as prediction risk, conventional regularization techniques are known to improve generalization when the data exhibits low-dimensional structure like sparsity. However, it is largely unexplored how to leverage this structure in the context of multi-objective learning (MOL) with multiple competing objectives. In this work, we discuss how the application of vanilla regularization approaches can fail, and propose a two-stage MOL framework that can successfully leverage low-dimensional structure. We demonstrate its effectiveness experimentally for multi-distribution learning and fairness-risk trade-offs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。