Best Arm Identification for Cascading Bandits in the Fixed Confidence Setting
Authors: Zixin Zhong, Wang Chi Cheung, Vincent Tan
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, extensive numerical simulations corroborate the efficacy of CASCADEBAI as well as the tightness of our upper bound on its time complexity. |
| Researcher Affiliation | Academia | 1Department of Mathematics, National University of Singapore, Singapore 2Department of Industrial Systems and Management, National University of Singapore, Singapore 3Institute of Operations Research and Analytics, National University of Singapore, Singapore 4Department of Electrical and Computer Engineering, National University of Singapore, Singapore. |
| Pseudocode | Yes | Algorithm 1 CASCADEBAI(ϵ, δ, K) |
| Open Source Code | No | The paper does not contain any explicit statement about the release of source code or a link to a code repository. |
| Open Datasets | No | The paper describes testing algorithms under 'various problem settings' and 'instances' with parameters like L and K, but does not use named public datasets or provide access information for any specific dataset used for training or evaluation. |
| Dataset Splits | No | The paper does not specify any dataset splits (e.g., train/validation/test percentages or counts) or cross-validation setup, only stating that '20 independent trials' were run. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running experiments (e.g., specific GPU/CPU models, memory, or cloud computing instances). |
| Software Dependencies | No | The paper does not provide specific software dependencies or version numbers (e.g., programming language, libraries, or solvers with version numbers) used for the experiments. |
| Experiment Setup | Yes | For each choice of algorithm and instance, we run 20 independent trials. The standard deviations of the time complexities of our algorithm are negligible compared to the averages, and therefore are omitted from the plots. More details are provided in Appendix E. [...] L = 64, K = 16, δ = 0.1 and ϵ = 0 in the cascading bandits. [...] L = 128, δ = 0.1, ϵ = 0, K = 20, . . . , 60. [...] We set the maximum time step as 10^7. |