Purushottam Kar

Purushottam Kar 

Purushottam Kar, Ph.D.
Consulting Researcher
Microsoft Research India, Bengaluru


Assistant Professor (on long leave)
Department of Computer Science and Engineering
The Indian Institute of Technology Kanpur


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.

Leave Notice: Starting August 2020, I am on long leave from IIT Kanpur.

News

  • [27 July 2021] [New] Our work developing the first algorithm for non-parametric regression with adversarially corrupted data and provable breakdown points under general conditions will appear at ECML 2021 and the Machine Learning journal. A preprint is available [here] and code will be released soon.

  • [12 May 2021] [New] Our work on Siamese networks for deep extreme classification with 100 million labels will appear at ICML 2021. Code for our method and a preprint will be linked [here].

  • [16 January 2021] [New] Our work on deep extreme classification with label graphs, that improves upon our previous work that uses label features alone, will appear at The Web Conference 2021 (formerly known as WWW). Code for our method and a preprint are linked [here].

  • [04 January 2021] [New] Our work on robust calibration of low-cost air quality monitoring sensors will appear in the journal Atmospheric Measurement Techniques. Code for our method and a link to the paper are available [here].

  • [16 December 2020] I delivered a keynote on deep learning for extreme-classification at the Amazon Research Days 2020 event. Slides for my talk are available [here].

  • [16 October 2020] Our work on deep extreme classification with label features with applications to large-scale product-to-product recommendation will appear at the WSDM 2021 conference. Code for our method and a preprint are linked [here].

  • [02 August 2020] Our work on Bayesian optimization techniques for designing effective lockdown and other non-pharmaceutical interventions to check the spread of pandemics such as CoViD-19 will appear in the Transactions of the INAE. Code for our method and a preprint are available [here].

  • [27 May 2020] Our work on accelerated program repair with applications to AI-based e-tutors for introductory programming courses will appear at AIED 2020. Code for our method and a preprint are available [here].

  • [02 June 2019] Our work on accelerating extreme classification algorithms that are used for recommendation and labelling tasks with millions of labels, will appear at IJCAI 2019. Code for our method and a preprint are available [here].

  • [25 March 2019] Check out our recent works on using the IRLS heuristic for robust regression (to appear in AISTATS 2019), and our work on bandit algorithms that are resilient to data corruption (to appear in the Machine Learning journal). Preprints are available [here].

  • [25 March 2019] Our monograph on non-convex optimization is a helpful guide to understanding the design and analysis of scalable algorithms for solving non-convex optimization problems in machine learning. Purchase the official copy [here] or get a free copy [here].