Date: June 24 2019.
Time: 04:30 PM to 06:00 PM (EDT)
Speaker: Mark Barlow
6600 Washington Ave. S.
Eden Prairie, Minnesota
United States 55344
Event Details & Registration: (URL)
Considering the massive number of devices, centralized machine learning via cloud computing incurs considerable overhead, and raises serious privacy concerns. Today, the consensus is that future machine learning tasks have to be performed starting from the network edge, namely devices. In this context, we will highlight key challenges in learning at the edge, including communication overhead, heterogeneity, and adversarial attacks. Wedding optimization techniques with system-level considerations, we will introduce novel methods for solving distributed learning problems. Our methods are simple to implement, and come with rigorous performance guarantees.
Tianyi Chen received the B. Eng. degree in Communication Science and Engineering from Fudan University, the M.Sc. and Ph.D degrees in Electrical and Computer Engineering (ECE) from the University of Minnesota (UMN), in 2014, 2016 and 2019, respectively. Starting in August 2019, he will with Department of ECSE at Rensselaer Polytechnic Institute (RPI) as an Assistant Professor. Between 2017 and 2018, he was a visiting scholar at Harvard University, University of California, Los Angeles, and University of Illinois Urbana-Champaign.
His research interests lie in optimization and machine learning with applications to large-scale networked systems such as Internet-of-Things, next-generation computing systems, and energy systems. He was a Best Student Paper Award finalist in the 2017 Asilomar Conf. on Signals, Systems, and Computers. He received the National Scholarship from China in 2013, the UMN ECE Department Fellowship in 2014, and the UMN Doctoral Dissertation Fellowship in 2017.