Harsh Pareek

Graduate Student
Department of Computer Science
GDC 4.718F
The University of Texas at Austin
Austin, TX 78712 USA

Phone:  (512) 994-5775

Email: harshp@cs.utexas.edu

About me

I'm a Fourth Year PhD student in Computer Science at UT Austin. I'm advised by Prof. Pradeep Ravikumar who runs the Statistical Machine Learning Lab. We're also part of the Center for Big Data Analytics. I graduated with a B.Tech. from IIT Bombay in 2011. As an undergraduate, I worked on Named Entity Recognition and Search on the Semantic Web.

I'm an avid reader. I've enjoy playing board games and have recently discovered collectible card games (My primary leisure activity in recent times has been Hearthstone). I participate in Lesswrong and the larger rationalist community. See here for a listing of my social profiles

NOTE: I'm looking for internships for Summer 2015. I'm interested in exploring problems at the intersection of Functional Analysis and Optimization in Machine Learning. My resume is here


  • The University of Texas at Austin, TX, USA
    Ph.D., Computer Science, Aug. 2016 (expected) (Advisor: Prof. Pradeep Ravikumar)

  • Indian Institute of Technology, Bombay, India
    B.Tech. with honours, Computer Science and Engineering, 2011 with Minor in Electrical Engineering


My general research focus is on optimization and graphical models. I enjoy research that focuses on application areas, but has a strong theoretical component. My work in this vein has thus far involved Learning to Rank and Human Computation as application areas. Please see my publications for details on these. I am also interested in and have done courses/projects involving Large Scale Learning (both high dimensional and big data settings), Time Series Analysis and NLP.

My current and upcoming work applies functional analysis and infinite dimensional optimization ideas, eg. our recent paper on A Representation Theory for Ranking Functions (see publications below). We are currently appyling these ideas to graphical models, contextual bandits and other problems.