Statistical Deficiency for Task Inclusion Estimation
This work addresses a foundational gap for researchers in transfer and multitask learning by providing a novel framework to analyze task relationships, though it appears incremental in building on existing statistical concepts.
The paper tackles the lack of tools for studying task structure in machine learning by proposing a theoretically grounded setup to define tasks and compute task inclusion using statistical deficiency, with results validated on synthetic data and applied to reconstruct the NLP pipeline.
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.