Abstract
Thanks to the ubiquitous nature of “diminishing returns” functions, submodular maximization is a central problem in unsupervised learning. We study this optimization problem in presence of practical considerations such as scalability, streaming nature of the data and robustness of the solution.
About the presenter
Morteza Zadimoghaddam
Research ScientistGoogle
Morteza Zadimoghaddam is a senior research scientist at Google Cambridge office. Prior to Google, he did his PhD in computer science at MIT (CSAIL) under supervision of Professor Erik D. Demaine. He works on applying optimization techniques to various practical problems in order to find provably efficient algorithms. In particular, he applies infrastructure optimization methods to save computational resources at scale. On the mathematical and research side, he is interested in Submodular Optimization and its applications in large scale data mining and machine learning problems.