Dynamic Pricing with Adversarially-Censored Demands
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909998304460800 |
|---|---|
| author | Xu, Jianyu Wang, Yining Chen, Xi Wang, Yu-Xiang |
| author_facet | Xu, Jianyu Wang, Yining Chen, Xi Wang, Yu-Xiang |
| contents | We study an online dynamic pricing problem where the potential demand at each time period $t=1,2,\ldots, T$ is stochastic and dependent on the price. However, a perishable inventory is imposed at the beginning of each time $t$, censoring the potential demand if it exceeds the inventory level. To address this problem, we introduce a pricing algorithm based on the optimistic estimates of derivatives. We show that our algorithm achieves $\tilde{O}(\sqrt{T})$ optimal regret even with adversarial inventory series. Our findings advance the state-of-the-art in online decision-making problems with censored feedback, offering a theoretically optimal solution against adversarial observations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06168 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Pricing with Adversarially-Censored Demands Xu, Jianyu Wang, Yining Chen, Xi Wang, Yu-Xiang Machine Learning Econometrics Optimization and Control 91B06, 91B24, 62P20, 62C20, 90B50 I.2.6; J.4 We study an online dynamic pricing problem where the potential demand at each time period $t=1,2,\ldots, T$ is stochastic and dependent on the price. However, a perishable inventory is imposed at the beginning of each time $t$, censoring the potential demand if it exceeds the inventory level. To address this problem, we introduce a pricing algorithm based on the optimistic estimates of derivatives. We show that our algorithm achieves $\tilde{O}(\sqrt{T})$ optimal regret even with adversarial inventory series. Our findings advance the state-of-the-art in online decision-making problems with censored feedback, offering a theoretically optimal solution against adversarial observations. |
| title | Dynamic Pricing with Adversarially-Censored Demands |
| topic | Machine Learning Econometrics Optimization and Control 91B06, 91B24, 62P20, 62C20, 90B50 I.2.6; J.4 |
| url | https://arxiv.org/abs/2502.06168 |