Pruning strategies in adaptive off-line tuning for optimized composition of components on heterogeneous systems
详细信息 查看全文
- 作者：Lu Li ; lu.li@liu.se" class="auth_mail" title="E-mail the corresponding author ; Usman Dastgeer usman.dastgeer@liu.se" class="auth_mail" title="E-mail the corresponding author ; Christoph Kessler christoph.kessler@liu.se" class="auth_mail" title="E-mail the corresponding author
- 关键词：Smart sampling ; Heterogeneous systems ; Component selection
- 刊名：Parallel Computing
- 出版年：2016
- 出版时间：January 2016
- 年：2016
- 卷：51
- 期：Complete
- 页码：37-45
- 全文大小：2083 K
文摘
- •
We consolidate our convexity assumption that forms the basis for adaptive pruning of the sampling space.
- •
We provide better control of trade-offs between sampling time, runtime overhead and accuracy in adaptive empirical modeling.
- •
Reducing training time and improving prediction accuracy can be achieved simultaneously.
- •
Our method can converge faster and reaches higher accuracy than random sampling.