Abstract
   Data-intensive applications have attracted considerable attention from researchers in information sciences and enterprises, as these applications have made evolutionary breakthroughs in scientific fields and are extremely valuable to produce productivity in businesses. Recently, as the high- speed growth of the new generated data, researchers have begun to leverage the useful knowledge hidden in such huge volume of data to optimize the performance of the data-intensive applications. However, optimize the performance of the data-intensive applications based on the data-driven approaches are still need to be explored. In this thesis, we focus on data-driven performance optimization for data-intensive applications. We first study an application, auto-labeling data on mobile devices. Second, we explore another data-intensive application, the cardinality estimation for numeric predicates in database systems. Furthermore, we also study the data loading problem for large-scale distributed training. Finally, we also study the cardinality estimation for string predicates. Overall, the evaluation results demonstrate enhanced performance, accuracy, and efficiency in several popular data-intensive applications. 
   

Biography
   Jie Liu is a Ph.D. candidate for EECS at UC Merced. Jie’s primary research interest lies in performance optimization for data-intensive applications. Particularly, his work focuses on optimizing the performance of some data-intensive applications, including data labeling, database, and deep learning training, etc, under the heterogenous memory environment. Jie’s research work is closely related to the industry. During his Ph.D study, he has four internships. His work have been published or submitted on some top conferences, such as VLDB, SEC, ATC, etc. He has a Master of Science from the University of Texas, Dallas, and a Bachelor of Computer Science from Northwestern Polytechnical University, China.