In this setting we study how to reduce the dimensionality of data for learning and for optimization, avoiding the “curse of dimensionality”.
In this setting we study how to model people’s preferences over a set of choices, and how to optimize and learn given user preferences in a variety of applications.
In this project we study how to make decisions in an unknown environment in an online setting.
In this work we apply matrix approximation theory to reduce the cost of training and deploying of dense layers in deep networks.
