File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.automatica.2025.112223
- Scopus: eid_2-s2.0-85218896760
- Find via
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Article: Stochastically constrained best arm identification with Thompson sampling
| Title | Stochastically constrained best arm identification with Thompson sampling |
|---|---|
| Authors | |
| Keywords | Best feasible arm identification Rate of posterior convergence Thompson sampling Top-two algorithm |
| Issue Date | 1-Jun-2025 |
| Publisher | Elsevier |
| Citation | Automatica, 2025, v. 176 How to Cite? |
| Abstract | We consider the problem of the best arm identification in the presence of stochastic constraints, where there is a finite number of arms associated with multiple performance measures. The goal is to identify the arm that optimizes the objective measure subject to constraints on the remaining measures. We will explore the popular idea of Thompson sampling (TS) as a means to solve it. To the best of our knowledge, it is the first attempt to extend TS to this problem. We will design a TS-based sampling algorithm, establish its asymptotic optimality in the rate of posterior convergence, and demonstrate its superior performance using numerical examples. |
| Persistent Identifier | http://hdl.handle.net/10722/355126 |
| ISSN | 2023 Impact Factor: 4.8 2023 SCImago Journal Rankings: 3.502 |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Yang, Le | - |
| dc.contributor.author | Gao, Siyang | - |
| dc.contributor.author | Li, Cheng | - |
| dc.contributor.author | Wang, Yi | - |
| dc.date.accessioned | 2025-03-27T00:35:36Z | - |
| dc.date.available | 2025-03-27T00:35:36Z | - |
| dc.date.issued | 2025-06-01 | - |
| dc.identifier.citation | Automatica, 2025, v. 176 | - |
| dc.identifier.issn | 0005-1098 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/355126 | - |
| dc.description.abstract | <p>We consider the problem of the best arm identification in the presence of stochastic constraints, where there is a finite number of arms associated with multiple performance measures. The goal is to identify the arm that optimizes the objective measure subject to constraints on the remaining measures. We will explore the popular idea of Thompson sampling (TS) as a means to solve it. To the best of our knowledge, it is the first attempt to extend TS to this problem. We will design a TS-based sampling algorithm, establish its asymptotic optimality in the rate of posterior convergence, and demonstrate its superior performance using numerical examples.</p> | - |
| dc.language | eng | - |
| dc.publisher | Elsevier | - |
| dc.relation.ispartof | Automatica | - |
| dc.subject | Best feasible arm identification | - |
| dc.subject | Rate of posterior convergence | - |
| dc.subject | Thompson sampling | - |
| dc.subject | Top-two algorithm | - |
| dc.title | Stochastically constrained best arm identification with Thompson sampling | - |
| dc.type | Article | - |
| dc.identifier.doi | 10.1016/j.automatica.2025.112223 | - |
| dc.identifier.scopus | eid_2-s2.0-85218896760 | - |
| dc.identifier.volume | 176 | - |
| dc.identifier.eissn | 1873-2836 | - |
| dc.identifier.issnl | 0005-1098 | - |