Task 009: Solving RNNs via Convex Programming

Abstract:

We propose a formulation for nonlinear recurrent models that includes simple parametric models of recurrent neural networks as a special case. The proposed formulation leads to a natural estimator in the form of a convex program. We provide a sample complexity for this estimator in the case of stable dynamics, where the nonlinear recursion has a certain contraction property, and under certain regularity conditions on the input distribution. 

 

Bio:

Sohail Bahmani is a postdoctoral fellow in the School of Electrical & Computer Engineering at Georgia Institute of Technology. His research interests are at the interface of optimization and statistics and relate to problems in machine learning, signal processing, and network analysis. He has received a best paper award from the AIStats conference in 2017 for his work on the phase retrieval problem. He also has made contributions to sparse optimization, inverse problems in imaging, and nonlinear regression. He earned his PhD from Carnegie Mellon University in 2013, his Master's degree from Simon Fraser University in 2008, and his Bachelor's degree from Sharif University of Technology in 2006, all in Electrical Engineering.