Rahul Kidambi

I am a graduate student of Prof. Sham M. Kakade studying Machine Learning at the University of Washington, Seattle.

Contact: rkidambi AT uw DOT edu.


My research centers around the design and analysis of scalable Algorithms for Machine Learning, as viewed through the lens of Optimization and Statistics.

I hold an active interest in the practical aspects of deep learning and non-convex optimization.

Previously, I worked on problems at the intersection of Structured Prediction, Semi-Supervised Learning and Active Learning.

Recent Papers/Preprints:

  • On the insufficiency of existing Momentum schemes for Stochastic Optimization,
    Rahul Kidambi, Praneeth Netrapalli, Prateek Jain and Sham M. Kakade.
    To Appear, International Conference on Learning Representations (ICLR), 2018. (Selected for Oral Presentation; 2% Acceptance Rate)
    Link to the manuscript/reviews: Open Review, January 2018.
    ArXiv manuscript, abs/1803.05591, March 2018.
    Code for Accelerated SGD: Git Repo.

  • Leverage Score Sampling for Faster Accelerated Regression and ERM,
    (α-β order) with Naman Agarwal, Sham M. Kakade, Yin Tat Lee, Praneeth Netrapalli and Aaron Sidford.
    ArXiv manuscript, abs/1711.08426, November 2017.

  • A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares),
    (α-β order) with Prateek Jain, Sham M. Kakade, Praneeth Netrapalli, Venkata Krishna Pillutla and Aaron Sidford.
    ArXiv manuscript, abs/1710.09430, October 2017.
    Invited paper at FSTTCS 2017.

  • Accelerating Stochastic Gradient Descent,
    (α-β order) with Prateek Jain, Sham M. Kakade, Praneeth Netrapalli and Aaron Sidford.
    ArXiv manuscript, abs/1704.08227, April 2017.
    Talk video: Sham at MSR.

  • Parallelizing Stochastic Approximation Through Mini-Batching and Tail Averaging,
    (α-β order) with Prateek Jain, Sham M. Kakade, Praneeth Netrapalli and Aaron Sidford.
    ArXiv manuscript, abs/1610.03774, October 2016.
    Accepted for journal publication pending minor revision, March 2017.

    The dblp listing provides a complete set of my papers.

    Academic Service:

  • Conference Reviewing: ISMB 2012, NIPS 2016, COLT 2017.
  • Journal Reviewing: Journal of Machine Learning Research (JMLR) - 2015, Electronic Journal of Statistics (EJS) - 2017.


    I have served as a Teaching Assistant for the following classes:

  • EE 514a: Information Theory-I (Autumn 2015).
  • EE 215: Fundamentals of Electrical Engineering (Autumn 2014, Winter 2015).

    Contact Information:

    Rahul Kidambi,
    Department of Electrical Engineering,
    185 Stevens Way, AE100R Campus Box 352500,
    University of Washington,
    Seattle, WA 98195-2500, USA.