Simple and near-optimal algorithms for hidden stratification and multi-group learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2021
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914834533056512 |
|---|---|
| author | Tosh, Christopher Hsu, Daniel |
| author_facet | Tosh, Christopher Hsu, Daniel |
| contents | Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2112_12181 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | Simple and near-optimal algorithms for hidden stratification and multi-group learning Tosh, Christopher Hsu, Daniel Machine Learning Multi-group agnostic learning is a formal learning criterion that is concerned with the conditional risks of predictors within subgroups of a population. The criterion addresses recent practical concerns such as subgroup fairness and hidden stratification. This paper studies the structure of solutions to the multi-group learning problem, and provides simple and near-optimal algorithms for the learning problem. |
| title | Simple and near-optimal algorithms for hidden stratification and multi-group learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2112.12181 |