LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929270995025920 |
|---|---|
| author | Wu, Yun-Ang Tsai, Yun-Da Lin, Shou-De |
| author_facet | Wu, Yun-Ang Tsai, Yun-Da Lin, Shou-De |
| contents | In this study, we delve into the Thresholding Linear Bandit (TLB) problem, a nuanced domain within stochastic Multi-Armed Bandit (MAB) problems, focusing on maximizing decision accuracy against a linearly defined threshold under resource constraints. We present LinearAPT, a novel algorithm designed for the fixed budget setting of TLB, providing an efficient solution to optimize sequential decision-making. This algorithm not only offers a theoretical upper bound for estimated loss but also showcases robust performance on both synthetic and real-world datasets. Our contributions highlight the adaptability, simplicity, and computational efficiency of LinearAPT, making it a valuable addition to the toolkit for addressing complex sequential decision-making challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06230 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem Wu, Yun-Ang Tsai, Yun-Da Lin, Shou-De Machine Learning In this study, we delve into the Thresholding Linear Bandit (TLB) problem, a nuanced domain within stochastic Multi-Armed Bandit (MAB) problems, focusing on maximizing decision accuracy against a linearly defined threshold under resource constraints. We present LinearAPT, a novel algorithm designed for the fixed budget setting of TLB, providing an efficient solution to optimize sequential decision-making. This algorithm not only offers a theoretical upper bound for estimated loss but also showcases robust performance on both synthetic and real-world datasets. Our contributions highlight the adaptability, simplicity, and computational efficiency of LinearAPT, making it a valuable addition to the toolkit for addressing complex sequential decision-making challenges. |
| title | LinearAPT: An Adaptive Algorithm for the Fixed-Budget Thresholding Linear Bandit Problem |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.06230 |