Common big data analytics strongly rely on distributed/parallel computing over a large number of servers. In such systems, communication for data shuffling is a main bottleneck that limits the overall execution time. In this talk, we are interested in the coded distributed computing recently proposed by Li et al. for the MapReduce-like framework. We will present how coding can reduce significantly the communication load, as well as our recent result on the optimal storage-computation-communication trade-off for the shared link setting. If time permits, we will further discuss how to design a distributed computing scheme from any placement delivery array (PDA) previously proposed for coded caching. This talk is based on joint works with Qifa Yan, Michele Wigger, and Xiaohu Tang.
Sheng Yang received the B.E. degree in electrical engineering from Jiaotong University, Shanghai, China, in 2001, and both the engineer degree and the M.Sc. degree in electrical engineering from Telecom ParisTech, Paris, France, in 2004, respectively. In 2007, he obtained his Ph.D. from Universite de Pierre et Marie Curie (Paris VI). From October 2007 to November 2008, he was with Motorola Research Center in Gif-sur-Yvette, France, as a senior staff research engineer. Since December 2008, he has joined CentraleSupelec where he is now a full professor. From April 2015, he also holds an honorary professorship in the department of electrical and electronic engineering of the University of Hong Kong (HKU). He received the 2015 IEEE ComSoc Young Researcher Award for the Europe, Middle East, and Africa Region (EMEA). He is an editor of the IEEE transactions on wireless communications.
23587040