Adaptive Double-Exploration Tradeoff for Outlier Detection
Authors: Xiaojin Zhang, Honglei Zhuang, Shengyu Zhang, Yuan Zhou6837-6844
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on both synthetic datasets and real-world datasets demonstrate the efficiency of our algorithm. In this section, we conduct experiments on both synthetic datasets and real datasets to show the performance of distinct algorithms. |
| Researcher Affiliation | Collaboration | Xiaojin Zhang,1 Honglei Zhuang,2 Shengyu Zhang,3 Yuan Zhou2 1The Chinese University of Hong Kong, 2University of Illinois Urbana-Champaign, 3Tencent |
| Pseudocode | Yes | Algorithm 1 Adaptive Double Exploration (ADE) |
| Open Source Code | No | The paper does not provide any explicit statement or link regarding the availability of its source code. |
| Open Datasets | Yes | We characterize the performance of distinct algorithms on the real dataset Hyun Catherines which is available at http://ir.ischool.utexas.edu/square/data.html. |
| Dataset Splits | No | The paper describes how synthetic datasets are generated and that '10 test cases independently' are created for each setting, but it does not specify any explicit training, validation, or test dataset splits for either the synthetic or real-world datasets. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments. |
| Software Dependencies | No | The paper does not provide any specific software dependencies with version numbers. |
| Experiment Setup | Yes | The confidence parameter δ is set as 0.1 and the results are averaged across ten independent simulations. We vary n as {100, 200, 400, 600, 800, 1000}, k is set as 2.5, the range of Δmin is [0.1, 0.2]. n is fixed as 900, k is set as 2. Since RR and WRR might take a long period of time to terminate, we speed up these two algorithms by pulling an arm 1,000 times at each round instead of pulling an arm once at each round. |