學術產出-期刊論文
| 題名 | Accelerating Item Factor Analysis on GPU with Python Package xifa |
| 作者 | 黃柏僩 Huang, Po-Hsien |
| 貢獻者 | 心理系 |
| 關鍵詞 | Item factor analysis; Item response theory; Deep learning; Parallel computing |
| 日期 | 2023-01 |
| 上傳時間 | 2023-05-29 |
| 摘要 | Item parameter estimation is a crucial step when conducting item factor analysis (IFA). From the view of frequentist estimation, marginal maximum likelihood (MML) seems to be the gold standard. However, fitting a high-dimensional IFA model by MML is still a challenging task. The current study demonstrates that with the help of a GPU (graphics processing unit) and carefully designed vectorization, the computational time of MML could be largely reduced for large-scale IFA applications. In particular, a Python package called xifa (accelerated item factor analysis) is developed, which implements a vectorized Metropolis–Hastings Robbins–Monro (VMHRM) algorithm. Our numerical experiments show that the VMHRM on a GPU may run 33 times faster than its CPU version. When the number of factors is at least five, VMHRM (on GPU) is much faster than the Bock–Aitkin expectation maximization, MHRM implemented by mirt (on CPU), and the importance-weighted autoencoder (on GPU). The GPU-implemented VMHRM is most appropriate for high-dimensional IFA with large data sets. We believe that GPU computing will play a central role in large-scale psychometric modeling in the near future. |
| 關聯 | Behavior Research Methods, Vol.55, pp.4403-4418 |
| 資料類型 | article |
| DOI | https://doi.org/10.3758/s13428-022-02024-x |
| dc.contributor | 心理系 | - |
| dc.creator (作者) | 黃柏僩 | - |
| dc.creator (作者) | Huang, Po-Hsien | - |
| dc.date (日期) | 2023-01 | - |
| dc.date.accessioned | 2023-05-29 | - |
| dc.date.available | 2023-05-29 | - |
| dc.date.issued (上傳時間) | 2023-05-29 | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/144834 | - |
| dc.description.abstract (摘要) | Item parameter estimation is a crucial step when conducting item factor analysis (IFA). From the view of frequentist estimation, marginal maximum likelihood (MML) seems to be the gold standard. However, fitting a high-dimensional IFA model by MML is still a challenging task. The current study demonstrates that with the help of a GPU (graphics processing unit) and carefully designed vectorization, the computational time of MML could be largely reduced for large-scale IFA applications. In particular, a Python package called xifa (accelerated item factor analysis) is developed, which implements a vectorized Metropolis–Hastings Robbins–Monro (VMHRM) algorithm. Our numerical experiments show that the VMHRM on a GPU may run 33 times faster than its CPU version. When the number of factors is at least five, VMHRM (on GPU) is much faster than the Bock–Aitkin expectation maximization, MHRM implemented by mirt (on CPU), and the importance-weighted autoencoder (on GPU). The GPU-implemented VMHRM is most appropriate for high-dimensional IFA with large data sets. We believe that GPU computing will play a central role in large-scale psychometric modeling in the near future. | - |
| dc.format.extent | 106 bytes | - |
| dc.format.mimetype | text/html | - |
| dc.relation (關聯) | Behavior Research Methods, Vol.55, pp.4403-4418 | - |
| dc.subject (關鍵詞) | Item factor analysis; Item response theory; Deep learning; Parallel computing | - |
| dc.title (題名) | Accelerating Item Factor Analysis on GPU with Python Package xifa | - |
| dc.type (資料類型) | article | - |
| dc.identifier.doi (DOI) | 10.3758/s13428-022-02024-x | - |
| dc.doi.uri (DOI) | https://doi.org/10.3758/s13428-022-02024-x | - |