提出统计缺陷视角下的任务包含度量方法，可评估任务间依赖关系。
Statistical Deficiency for Task Inclusion Estimation
- 从统计缺陷角度定义任务，构建任务包含关系的理论框架。
- 设计信息充分性代理指标，可有效估计任务间的包含程度。
- 适用于理解模型能力边界，适合研究多任务学习与模型泛化者。
任务是机器学习中的核心概念，是评估模型能力最自然的单位。当前趋势是构建能应对任意任务的通用模型。尽管迁移学习和多任务学习试图利用任务空间的内在结构，但缺乏可靠的工具来分析其结构。本文提出一个理论严谨的框架，用于定义任务，并从统计缺陷的角度计算两个任务之间的包含关系。我们提出了一个可计算的代理指标——信息充分性，用于估计任务间的包含程度，在合成数据上验证了其有效性，并成功重建了经典的自然语言处理流水线。
原文摘要 · Abstract (English)
Tasks are central in machine learning, as they are the most natural objects to assess the capabilities of current models. The trend is to build general models able to address any task. Even though transfer learning and multitask learning try to leverage the underlying task space, no well-founded tools are available to study its structure. This study proposes a theoretically grounded setup to define the notion of task and to compute the {\bf inclusion} between two tasks from a statistical deficiency point of view. We propose a tractable proxy as information sufficiency to estimate the degree of inclusion between tasks, show its soundness on synthetic data, and use it to reconstruct empirically the classic NLP pipeline.
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。