多任务学习通过隐式正则化提升泛化能力，延缓并缓解双下降现象。
Asymptotic Behavior of Multi--Task Learning: Implicit Regularization and Double Descent Effects
- 多任务学习等价于带额外正则项的传统模型，实现隐式正则化。
- 实证发现多任务结合可推迟双下降拐点，长期降低泛化误差。
- 适合关注泛化性能优化与模型鲁棒性的研究者参考。
多任务学习旨在通过共享多个相关任务的共同信息来改善泛化误差。其主要挑战在于识别能揭示不同但相关任务间共享信息的建模范式。本文对一种与误设感知机模型相关的流行多任务范式进行了精确的渐近分析。核心贡献是明确揭示了融合多个相关任务带来优势的根本原因：组合多任务在渐近意义上等价于带有额外正则项的传统形式，该正则项有助于提升泛化性能。另一贡献是实证研究了任务组合对泛化误差的影响。特别地，我们实证表明，多任务结合可推迟双下降现象，并能在渐近条件下缓解该现象。
原文摘要 · Abstract (English)
Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common information shared between different but related tasks. This paper provides a precise asymptotic analysis of a popular multi--task formulation associated with misspecified perceptron learning models. The main contribution of this paper is to precisely determine the reasons behind the benefits gained from combining multiple related tasks. Specifically, we show that combining multiple tasks is asymptotically equivalent to a traditional formulation with additional regularization terms that help improve the generalization performance. Another contribution is to empirically study the impact of combining tasks on the generalization error. In particular, we empirically show that the combination of multiple tasks postpones the double descent phenomenon and can mitigate it asymptotically.
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。