报告题目：Towards Effective Data Analysis with Low Complexity
报 告 人：张国强博士（悉尼科技大学）
Guoqiang Zhang received the Bachelor degree from the University of Science and Technology of China (USTC) in 2003, a master of philosophy (M.Phil.) from the University of Hong Kong in 2006, and his PhD degree from the Royal Institute of Technology – KTH in 2010. He then worked as a post-doctoral researcher at Delft University of Technology full time until the end of 2014 and part time until the end of 2016. From 2015 to 2016, he worked as a senior researcher at Ercisson AB, Sweden. He is now working as a senior lecturer at the University of Technology Sydney. His current research interests include large scale distributed optimization, optimization in deep learning, and active noise control.
In recent years, data analytics has attracted increasing research attention due to ubiquitous computing units and various emerging data-driven applications originating from, for example, sensor networks, social media, and online-shopping. It is expected that data analytics will become increasingly important in the near future along with the rapid growth of artificial intelligence (AI). Design of simple but effective algorithms is the essential step to allow for effective data analysis. In the talk, we consider algorithmic design for three research topics, which are (1) distributed and parallel data analysis, (2) effective training of deep neural networks, and (3) decentralized active noise control (ANC). For each topic, its background and the algorithmic design principles will be briefly summarized.