Rishabh Iyer; Submodular Combinatorial Problems in Machine Learning: Algorithms and Applications

April 8, 2014, 4:00pm
EEB 303
Rishabh IyerDepart­ment of Electrical Engineering, UW. 
Submodular Combinatorial Problems in Machine Learning: Algorithms and Applications

Abstract: Having long been recognized in combinatorics, the concept of submodularity is becoming increasingly important in machine learning, since it can capture intuitive and yet nontrivial interactions between variables. This expressiveness has found many applications in machine learning, particularly in understanding structured data like text, vision and speech. Submodular functions naturally capture aspects of information, coverage and diversity in maximization problems, while also modeling notions of cooperation, sparsity, complexity and economies of scale in minimization problems. In this talk, we shall consider a large class of submodular optimization problems and motivate them with several real world applications, particularly in machine learning. We shall then provide a unifying algorithmic framework for solving several of these optimization problems, and highlight the scalability and practicality of this approach. We shall also highlight novel theoretical characterizations, which provide better connections between theory and practice. We shall ground this entire talk with a large number of applications in machine learning, including image segmentation, image correspondence, image collection summarization, feature selection, and data subset selection. This talk should be self contained and shall not require prior knowledge of submodular functions and optimization.

This is based on joint work with Jeff Bilmes, Stefanie Jegelka, Sebastian Tschiatschek and Kai Wei.

Bio: Rishabh Iyer is a Ph.D candidate at the University of Washington, Seattle, where he works with Jeff Bilmes. His main interests are in theoretical and applied aspects of Discrete Optimization and specifically submodularity  with applications in Machine Learning, Computer Vision and Speech. He received his MS from University of Washington in 2013, and his B.Tech from IIT-Bombay in 2011. He has been a visitor at Microsoft Research, Redmond and Simon Fraser University. His work on submodular optimization has received numerous awards including the Microsoft Research Fellowship award, the Facebook Fellowship award and best paper awards at the International Conference for Machine Learning (ICML) and Neural Information Processing Systems (NIPS).

Leave a Reply

Your email address will not be published. Required fields are marked *