Hyper-Parameter Optimization
摘要
The quality of machine learning models largely depends on their hyper-parameter configurations. However, finding proper hyper-parameter configurations for machine learning algorithms/systems is challenging and requires much resources. This project aims to research on novel hyper-parameter optimization techniques to support efficient machine learning systems.
项目成员
文泽忆
助理教授
出版文章
1. Efficient Hyperparameter Optimization with Adaptive Fidelity Identification. Jiantong Jiang*, Zeyi Wen, Atif Mansoor, and Ajmal Saeed Mian. IEEE/CVPR 2024
2. Enhancing the Performance of Bandit-based Hyperparameter Optimization. Yile Chen, Zeyi Wen*, Jian Chen*, and Jin Huang.
项目周期
2022-Present
研究领域
Data-driven AI & Machine Learning、High-Performance Systems for Data Analytics
关键词
Hyper-parameter Optimization, Machine Learning, Resource Efficiency