Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.05491 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909902870413312 |
|---|---|
| author | Fosse, Loïc Béchet, Frédéric Favre, Benoît Damnati, Géraldine Lecorvé, Gwénolé Darrin, Maxime Formont, Philippe Piantanida, Pablo |
| author_facet | Fosse, Loïc Béchet, Frédéric Favre, Benoît Damnati, Géraldine Lecorvé, Gwénolé Darrin, Maxime Formont, Philippe Piantanida, Pablo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_05491 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Statistical Deficiency for Task Inclusion Estimation Fosse, Loïc Béchet, Frédéric Favre, Benoît Damnati, Géraldine Lecorvé, Gwénolé Darrin, Maxime Formont, Philippe Piantanida, Pablo Machine Learning 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. |
| title | Statistical Deficiency for Task Inclusion Estimation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.05491 |