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 problems at the intersection of statistics, optimization and machine learning, in particular on aspects of aligning the objectives of the ML models with those of humans. Before coming to Berkeley, I spent 2 wonderful years working at Microsoft Research Bangalore 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) Google Scholar    DBLP

Publications

• Agnostic learning with unknown utilities
  Kush Bhatia, Peter L. Bartlett, Anca D. Dragan, and Jacob Steinhardt,
  Innovations in Theoretical Computer Science (ITCS), 2021
  

• Preference learning along multiple criteria: A game-theoretic perspective
  Kush Bhatia, Ashwin Pananjady, Peter L. Bartlett, Anca D. Dragan, and Martin J. Wainwright,
  Neural Information Processing Systems (NeurIPS), 2020
  ICML workshop on Theoretical Foundations of Reinforcement Learning (oral), 2020
  [pdf]

• Online learning with dynamics: A minimax perspective
  Kush Bhatia, and Karthik Sridharan,
  Neural Information Processing Systems (NeurIPS), 2020
  [pdf]

• Bayesian Robustness: A Nonasymptotic Viewpoint
  Kush Bhatia, Yi-An Ma, Anca D. Dragan, Peter L. Bartlett, and Michael I. Jordan,
  Under Review, 2019
  [pdf]

• Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
  Arun Sai Suggala, Kush Bhatia, Pradeep Ravikumar, and Prateek Jain,
  Conference on Learning Theory (COLT), 2019
  [pdf]

• POLITEX: Regret Bounds for Policy Iteration using Expert Prediction
  Yasin Abbasi-Yadkori, Peter L. Bartlett, Kush Bhatia, Nevena Lazic, Csaba Szepesvári, and Gellért Weisz,
  International Conference on Machine Learning (ICML), 2019
  [pdf]

• Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
  Dhruv Malik, Ashwin Pananjady, Kush Bhatia, Koulik Khamaru, Peter L. Bartlett, and Martin J. Wainwright,
  Journal of Machine Learning Research (JMLR), Jan 2020
  Preliminary version at: International Conference on Artificial Intelligence and Statistics (AISTATS), 2019
  [pdf]

• Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation
  Kush Bhatia, Aldo Pacchiano, Nicolas Flammarion, Peter L. Bartlett, and Michael I. Jordan,
  Neural Information Processing Systems (NeurIPS), 2018
  [pdf]

• FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
  Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, and Manik Varma,
  Neural Information Processing Systems (NeurIPS), 2018
  [pdf] [Code] [Short Video] [Blog]

• Establishing Appropriate Trust Via Critical States.
  Sandy Huang, Kush Bhatia, Pieter Abbeel, and Anca D. Dragan,
  International Conference on Intelligent Robots and Systems (IROS), 2018
  [pdf]

• Consistent Robust Regression
  Kush Bhatia, Prateek Jain, Parameswaran Kamalaruban, and Purushottam Kar,
  Neural Information Processing Systems (NIPS), 2017
  [pdf] [Short Video]

• Robust Regression via Hard Thresholding
  Kush Bhatia, Prateek Jain, and Purushottam Kar,
  Neural Information Processing Systems (NIPS), 2015
  [pdf]

• Sparse Local Embeddings for Extreme Multi-label Classification
  Kush Bhatia, Himanshu Jain, Purushottam Kar, Manik Varma, and Prateek Jain,
  Neural Information Processing Systems (NIPS), 2015
  [pdf] [Code] [Extreme Classification Repository]

• Lazy Generic Cuts
  Dinesh Khandelwal, Kush Bhatia, Chetan Arora and Parag Singla,
  Computer Vision and Image Understanding, 2016
  [pdf]