Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910773930885120 |
|---|---|
| author | Lin, Jiabin Moothedath, Shana Vaswani, Namrata |
| author_facet | Lin, Jiabin Moothedath, Shana Vaswani, Namrata |
| contents | We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T contextual linear bandits with dimension d simultaneously, and these T bandit tasks collectively share a common linear representation with a dimensionality of r much smaller than d. We present a new algorithm based on alternating projected gradient descent (GD) and minimization estimator to recover a low-rank feature matrix. Using the proposed estimator, we present a multi-task learning algorithm for linear contextual bandits and prove the regret bound of our algorithm. We presented experiments and compared the performance of our algorithm against benchmark algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_02068 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits Lin, Jiabin Moothedath, Shana Vaswani, Namrata Machine Learning We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T contextual linear bandits with dimension d simultaneously, and these T bandit tasks collectively share a common linear representation with a dimensionality of r much smaller than d. We present a new algorithm based on alternating projected gradient descent (GD) and minimization estimator to recover a low-rank feature matrix. Using the proposed estimator, we present a multi-task learning algorithm for linear contextual bandits and prove the regret bound of our algorithm. We presented experiments and compared the performance of our algorithm against benchmark algorithms. |
| title | Fast and Sample Efficient Multi-Task Representation Learning in Stochastic Contextual Bandits |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2410.02068 |