Decentralized Optimization by First-Order Methods
Apr 14, 2014
from 01:00 PM to 02:30 PM
|Where||Engr. IV Bldg., Shannon Room 54-134|
|Contact Name||Prof. Christina Fragouli|
|Add event to calendar||
Prof. Wotao Yin
There has been considerable recent interest in solving optimization problems with data stored over a network. For these problems we need techniques that process data locally yet converge rapidly to an (approximate) solution across the entire network. This talk covers primarily first-order algorithms for large-scale optimization of the decentralized type. We emphasize skillful uses of gradient, proximal, duality, and splitting techniques so that massively parallel algorithms can be developed. Theoretical bounds and numerical results will be presented to demonstrate the scalability of the proposed algorithms.
Wotao Yin is a professor in the Department of Mathematics at UCLA. His research interests lie in computational optimization and its applications in image processing, machine learning, and other inverse problems. He received his B.S. in mathematics from Nanjing University in 2001, and then M.S. and Ph.D. in operations research from Columbia University in 2003 and 2006, respectively. During 2006 - 2013, he was with Rice University. He won NSF CAREER award in 2008 and Alfred P. Sloan Research Fellowship in 2009. He joined UCLA in July 2013. His recent work has been in optimization algorithms for large-scale and distributed signal processing and machine learning problems.