Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits
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_ | 1866911946321690624 |
|---|---|
| author | He, Yuchen Ye, Zichun Zhang, Chihao |
| author_facet | He, Yuchen Ye, Zichun Zhang, Chihao |
| contents | We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m<n$ arms and their statistics can be stored in the memory. We give a complete characterization of the optimal regret in terms of $m, n$ and $P$. Specifically, we design an algorithm with $\tilde O\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ regret and complement it with an $\tilde Ω\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ lower bound when the number of rounds $T$ is sufficiently large. Our results are tight up to a logarithmic factor in $n$ and $P$. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_19752 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits He, Yuchen Ye, Zichun Zhang, Chihao Machine Learning Data Structures and Algorithms We study the stochastic multi-armed bandit problem in the $P$-pass streaming model. In this problem, the $n$ arms are present in a stream and at most $m<n$ arms and their statistics can be stored in the memory. We give a complete characterization of the optimal regret in terms of $m, n$ and $P$. Specifically, we design an algorithm with $\tilde O\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ regret and complement it with an $\tilde Ω\left((n-m)^{1+\frac{2^{P}-2}{2^{P+1}-1}} n^{\frac{2-2^{P+1}}{2^{P+1}-1}} T^{\frac{2^P}{2^{P+1}-1}}\right)$ lower bound when the number of rounds $T$ is sufficiently large. Our results are tight up to a logarithmic factor in $n$ and $P$. |
| title | Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits |
| topic | Machine Learning Data Structures and Algorithms |
| url | https://arxiv.org/abs/2405.19752 |