Kush Bhatia

Kush Bhatia 

I am a graduate student in the Computer Science department at UC Berkeley where I am fortunate to be advised by Peter Bartlett and Anca Dragan. I am interested in research problems at the intersection of statistics, optimization and machine learning.

Before coming to Berkeley, I spent 2 wonderful years working at Microsoft Research India with Prateek Jain and Manik Varma. I completed my undergraduate studies at IIT Delhi with a major in Computer Science where I was advised by Parag Singla for my undergraduate thesis.

Email: first_name [at] cs [dot] berkeley [dot] edu (where first_name = kush)

Publications

Refereed Conference Publications

  1. Consistent Robust Regression
    Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, and Purushottam Kar,
    in Proceedings of the 30th Annual Conference on Advances in Neural Information Processing Systems (NIPS), 2017

  2. Robust Regression via Hard Thresholding
    Kush Bhatia, Prateek Jain, and Purushottam Kar,
    in Proceedings of the 28th Annual Conference on Advances in Neural Information Processing Systems (NIPS), 2015
    [pdf]

  3. Sparse Local Embeddings for Extreme Multi-label Classification
    Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain,
    in Proceedings of the 28th Annual Conference on Advances in Neural Information Processing Systems (NIPS), 2015
    [pdf] [URL]

Refereed Journal Publications

  1. Lazy Generic Cuts
    Dinesh Khandelwal, Kush Bhatia, Chetan Arora and Parag Singla,
    Computer Vision and Image Understanding, (143), pp.80-91, 2016
    [pdf]

Collaborators

I have been fortunate to collaborate with people who are awesome researchers and amazing to interact with. So, I decided to maintain a list in chronological order of my introduction with them:
Markus Pueschel, Manik Varma, Parag Singla, Chetan Arora, Prateek Jain, Purushottam Kar, Deeparnab Chakrabarty, Aditya Nori, Peter Bartlett, Anca Dragan