Purushottam Kar

Purushottam Kar 

Purushottam Kar, Ph.D.
Postdoctoral Research Fellow
Machine Learning and Optimization Group
Microsoft Research India


Welcome to my homepage. You will find my contact details and some articles and talks of mine on this site.
Please use the links on the left hand menu to navigate.

News

  • [27 Jun 2015] I have been given a reviewer award by the International Conference on Machine Learning (ICML) for my reviewing work for the 2015 edition of the conference.

  • [26 Jun 2015] Delivered an introductory tutorial on statistical learning theory and concentration at the MSR Summer School on Machine Learning at IISc. Tutorial video and slides would be available here.

  • [25 Apr 2015] Two papers to appear at ICML 2015. One paper deals with improved stochastic optimization techniques for two specific classes of structured loss functions. This supersedes our earlier NIPS 2014 paper for these classes of loss functions. The second paper deals with maximizing precision at the top for bipartite ranking problems.

  • [16 Dec 2014] My Ph.D. thesis has been given the IUPRAI Doctoral Dissertation Award for the year 2014.

  • [9 Sep 2014] Two papers to appear at NIPS 2014 - download preprints here. One paper deals with high dimensional statistical estimation using projected gradient methods. The second paper deals with online and stochastic methods for structured loss functions such as ranking losses, F-measure etc.

  • [26 Jul 2013] Check out my Microsoft Research homepage [url]. It is a temporary homepage but will have some recent updates such as talk slides and recent publications. The CSE/IITK webpage shall continue to be my primary homepage for some more time.

  • [23 Jul 2013] I have joined Microsoft Research India as a Research Fellow. This is a post-doctoral position and I will be employed here till July 2015. My Email ID given here will continue to work as my primary point of contact.

  • [15 Sep 2009] The CSE Department, IIT Kanpur has a reading group in Machine learning. You can have a look at the talks presented in the group meetings at the SIGML homepage [url]..