Prof. Piyush Rai, who recently joined Computer Science & Engineering department, IIT Kanpur, will be offering two mini-courses as a set of a total 4 tutorials (each of about 1.5 hrs). Below is the detail regarding the courses. All of you are invited for these exciting courses.



Mini-course on probabilistic and Bayesian modeling

We will have 2 tutorials (each will be for about one hour 30 minutes) on the following topics:

1) Probabilistic generative modeling, priors, likelihood, posterior, conjugate family, parameter estimation (MLE, MAP, fully Bayesian).
2) Case study: Bayesian sparse linear regression

Venue : RM 101
Date : Nov 3 , Tuesday (5:00 PM - 6:30 PM)
           Nov 5 , Thursday (5:00 PM - 6:30 PM )



Mini-course on non-parametric Bayesian modeling

We will have 2 tutorials (each will be for about one hour 30 minutes) on the following topics:

1) Introduction to Gaussian Process (GP) and applications to regression and classification problems (or function approximation in general).
2) Introduction to Dirichlet Process (DP) and application to mixture modeling. Introduction to Beta Process (BP) and applications to sparse
latent feature modeling.

Venue : RM 101
Date : Nov 7 ,Saturday (5:00 PM - 6:30 PM)
           Nov 8 , Sunday (5:00 PM - 6:30 PM)


Prof. Piyush Rai did his PhD (2007-2012) in Computer Science from School of Computing, University of Utah. Thereafter, for a year, he was a postdoc jointly with the Computer Science and the Statistics & Data Science department at UT Austin, and then an Assistant Research Professor in Electrical & Computer Engineering at Duke University, where he is now an Adjunct Assistant Professor. His primary area of research is in machine learning and Bayesian statistics. His research focuses on probabilistic modeling of massive and complex data, where the complexity may be manifested in form of one or more of the following data characteristics: high-dimensional, heterogeneous and multi-modal, relational, streaming, sequential, time-evolving, heavy-tailed, etc. He applies his work to solve problems in a wide range of areas, such as statistical NLP, IR, computer vision, healthcare analytic, econometric, computational biology, computational neuroscience, and computer systems (e.g., compilers, networks, security).