Special Seminar – Guanghui (George) Lan
Title – Decentralized stochastic gradient descent and beyond
Stochastic gradient descent (SGD) methods have recently found wide applications in large-scale data analysis, especially in machine learning. These methods are very attractive to process online streaming data as they scan through the dataset only once but still generate solutions with acceptable accuracy. However, it is known that classical SGD methods are ineffective in processing streaming data distributed over multi-agent network systems (e.g., sensor and social networks), mainly due to the high communication costs incurred by these methods. In this talk, we present a new class of SGD methods, referred to as stochastic decentralized communication sliding methods, which can significantly reduce the aforementioned communication costs for decentralized stochastic optimization and machine learning. We show that these methods can skip inter-node communications while performing SGD iterations. As a result, they require a substantially smaller number of communication rounds than existing decentralized SGD, while the total number of required stochastic subgradient computations are comparable to those optimal bounds achieved by classical centralized SGD type methods. We also develop new variants of these methods that can achieve graph topology invariant gradient/sampling complexity when the problem is smooth and samples can be stored locally.
BIO: Guanghui (George) Lan is an associate professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Institute of Technology since January 2016. Dr. Lan was on the faculty of the Department of Industrial and Systems Engineering at the University of Florida from 2009 to 2015, after earning his Ph.D. degree from Georgia Institute of Technology in August 2009. His main research interests lie in optimization and machine learning. The academic honors he received include the Mathematical Optimization Society Tucker Prize Finalist (2012), INFORMS Junior Faculty Interest Group Paper Competition First Place (2012) and the National Science Foundation CAREER Award (2013). Dr. Lan serves as an associate editor for Mathematical Programming, SIAM Journal on Optimization and Computational Optimization and Applications. He is also an associate director of the Center for Machine Learning at Georgia Tech.
For Zoom information email Meg Tully – [email protected]