Active Learning for Fair and Stable Online Allocations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866929393504354304 |
|---|---|
| author | Bhattacharya, Riddhiman Nguyen, Thanh Sun, Will Wei Tawarmalani, Mohit |
| author_facet | Bhattacharya, Riddhiman Nguyen, Thanh Sun, Will Wei Tawarmalani, Mohit |
| contents | We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of the online resource allocation process. Despite this restriction, our proposed algorithms provide regret bounds that are sub-linear in number of time-periods for various measures that include fairness metrics commonly used in resource allocation problems and stability considerations in matching mechanisms. The key insight of our algorithms lies in adaptively identifying the most informative feedback using dueling upper and lower confidence bounds. With this strategy, we show that efficient decision-making does not require extensive feedback and produces efficient outcomes for a variety of problem classes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_14784 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Active Learning for Fair and Stable Online Allocations Bhattacharya, Riddhiman Nguyen, Thanh Sun, Will Wei Tawarmalani, Mohit Machine Learning Other Statistics We explore an active learning approach for dynamic fair resource allocation problems. Unlike previous work that assumes full feedback from all agents on their allocations, we consider feedback from a select subset of agents at each epoch of the online resource allocation process. Despite this restriction, our proposed algorithms provide regret bounds that are sub-linear in number of time-periods for various measures that include fairness metrics commonly used in resource allocation problems and stability considerations in matching mechanisms. The key insight of our algorithms lies in adaptively identifying the most informative feedback using dueling upper and lower confidence bounds. With this strategy, we show that efficient decision-making does not require extensive feedback and produces efficient outcomes for a variety of problem classes. |
| title | Active Learning for Fair and Stable Online Allocations |
| topic | Machine Learning Other Statistics |
| url | https://arxiv.org/abs/2406.14784 |