Raman Arora is an assistant professor in computer science and a member of the Mathematical Institute for Data Science, the Center for Language and Speech Processing, and the Institute for Data Intensive Engineering and Science.
He is interested in machine learning; statistical signal processing; stochastic approximation algorithms; and applications to speech and language processing, and his research focuses on developing representation learning techniques that can capitalize on unlabeled data, which is often cheap and abundant and virtually unlimited. The goal of these techniques is to learn a representation that reveals intrinsic low-dimensional structure in data, disentangles underlying factors of variation in data by incorporating universal priors such as smoothness and sparsity and is useful across multiple tasks and domains.
Arora earned his MS and PhD degrees in Electrical and Computer Engineering from the University of Wisconsin-Madison in 2005 and 2009, respectively. From 2009 to 2011, he was a postdoctoral research associate at the University of Washington and a visiting researcher at Microsoft Research Redmond. He came to Johns Hopkins from Toyota Technological Institute at Chicago, where he was a research assistant professor and postdoctoral scholar.