Balaji Lakshminarayanan

Hello! I am a Senior Research Scientist at Google DeepMind in Mountain View (USA), working on Machine Learning and its applications.

My research interests are in scalable, probabilistic machine learning. My PhD thesis [17] was focused on exploring (and exploiting :)) connections between neat mathematical ideas in (non-parametric) Bayesian land and computationally efficient tricks in decision tree land, to get the best of both worlds.

More recently, I have focused on:

Quick Links

Brief Bio

Before joining DeepMind, I was a PhD student at Gatsby Unit, CSML, University College London, working with Yee Whye Teh. Between 2008-10, I was a Masters student at Oregon State University. During my undergrad, I was lucky to be part of the Integrated Systems laboratory, where I worked on communication sub-systems for the Anna University Micro-satellite (ANUSAT) project, India's first student-built satellite.


Here's my Google Scholar page.

  1. Clinically applicable deep learning for diagnosis and referral in retinal disease
    Jeffrey De Fauw, Joseph R Ledsam, Bernardino Romera-Paredes, Stanislav Nikolov, Nenad Tomasev, Sam Blackwell, Harry Askham, Xavier Glorot, Brendan O'Donoghue, Daniel Visentin, George van den Driessche, Balaji Lakshminarayanan, Clemens Meyer, Faith Mackinder, Simon Bouton, Kareem Ayoub, Reena Chopra, Dominic King, Alan Karthikesalingam, Cían O Hughes, Rosalind Raine, Julian Hughes, Dawn A Sim, Catherine Egan, Adnan Tufail, Hugh Montgomery, Demis Hassabis, Geraint Rees, Trevor Back, Peng T. Khaw, Mustafa Suleyman, Julien Cornebise, Pearse A. Keane, Olaf Ronneberger
    Nature Medicine, 2018
    [link] [blog]

  2. Learning from delayed outcomes with intermediate observations
    Timothy Mann, Sven Gowal, Ray Jiang, Huiyi Hu, Balaji Lakshminarayanan and Andras Gyorgy

  3. Distribution matching in variational inference
    Mihaela Rosca, Balaji Lakshminarayanan and Shakir Mohamed

  4. Many paths to equilibrium: GANs do not need to decrease a divergence at every step
    William Fedus*, Mihaela Rosca*, Balaji Lakshminarayanan, Andrew Dai, Shakir Mohamed and Ian Goodfellow
    ICLR, 2018

  5. Variational approaches for auto-encoding generative adversarial networks
    Mihaela Rosca*, Balaji Lakshminarayanan*, David Warde-Farley and Shakir Mohamed
    * denotes equal contribution

  6. The Cramer distance as a solution to biased Wasserstein gradients
    Marc G. Bellemare, Ivo Danihelka, Will Dabney, Shakir Mohamed, Balaji Lakshminarayanan, Stephan Hoyer and Remi Munos

  7. Comparison of maximum likelihood and GAN-based training of Real NVPs
    Ivo Danihelka, Balaji Lakshminarayanan, Benigno Uria, Daan Wierstra and Peter Dayan

  8. Simple and scalable predictive uncertainty estimation using deep ensembles
    Balaji Lakshminarayanan, Alexander Pritzel and Charles Blundell
    NIPS, 2017
    [arXiv] [slides] [poster]
    Note: A version of this work was presented at the NIPS workshop on Bayesian deep learning, 2016.

  9. Learning in implicit generative models
    Shakir Mohamed* and Balaji Lakshminarayanan*
    * denotes equal contribution
    Note: A version of this work was presented at the NIPS workshop on adversarial training, 2016.

  10. Learning deep nearest neighbor representations using differentiable boundary trees
    Daniel Zoran, Balaji Lakshminarayanan and Charles Blundell

  11. Distributed Bayesian learning with stochastic natural-gradient expectation propagation and the posterior server
    Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell and Yee Whye Teh
    JMLR, 2017
    [arXiv] [code]

  12. Decision trees and forests: a probabilistic perspective
    Balaji Lakshminarayanan
    Ph.D. thesis, University College London, 2016

  13. The Mondrian kernel
    Matej Balog, Balaji Lakshminarayanan, Zoubin Ghahramani, Daniel M. Roy and Yee Whye Teh
    UAI, 2016
    [arXiv] [code] [slides] [poster]

  14. Approximate inference with the variational Holder bound
    Guillaume Bouchard and Balaji Lakshminarayanan

  15. Mondrian forests for large-scale regression when uncertainty matters
    Balaji Lakshminarayanan, Daniel M. Roy and Yee Whye Teh
    AISTATS, 2016
    [pdf] [code] [slides]

  16. Kernel-based just-in-time learning for passing expectation propagation messages
    Wittawat Jitkrittum, Arthur Gretton, Nicolas Heess, Ali Eslami, Balaji Lakshminarayanan, Dino Sejdinovic and Zoltan Szabo
    UAI, 2015
    [arXiv] [code]

  17. Particle Gibbs for Bayesian additive regression trees
    Balaji Lakshminarayanan, Daniel M. Roy and Yee Whye Teh
    AISTATS, 2015
    [pdf] [code]

  18. Mondrian forests: Efficient online random forests
    Balaji Lakshminarayanan, Daniel M. Roy and Yee Whye Teh
    NIPS, 2014
    [pdf] [code] [slides]
    Note: See here for a much faster, scikit-learn compatible re-implementation of Mondrian forests.

  19. Distributed Bayesian posterior sampling via moment sharing
    Minjie Xu, Balaji Lakshminarayanan, Yee Whye Teh, Jun Zhu and Bo Zhang
    NIPS, 2014
    [pdf] [code]

  20. Latent IBP compound Dirichlet allocation
    Cedric Archambeau, Balaji Lakshminarayanan, and Guillaume Bouchard
    TPAMI special issue on Bayesian Nonparametrics, 2015
    [pdf] [code available upon request] [IEEE link]
    Note: A short version of this work appeared at the NIPS workshop on Bayesian nonparametrics, 2011.

  21. Inferring ground truth from multi-annotator ordinal data: a probabilistic approach
    Balaji Lakshminarayanan and Yee Whye Teh
    [arXiv] [code]

  22. Top-down particle filtering for Bayesian decision trees
    Balaji Lakshminarayanan, Daniel M. Roy and Yee Whye Teh
    ICML, 2013
    [pdf] [code] [slides]

  23. Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach
    Forrest Briggs, Balaji Lakshminarayanan, Lawrence Neal, Xiaoli Z. Fern, Raviv Raich, Sarah J. K. Hadley, Adam S. Hadley, and Matthew G. Betts
    JASA, 2012

  24. Inference in supervised latent Dirichlet allocation
    Balaji Lakshminarayanan and Raviv Raich
    MLSP, 2011
    [pdf] [code available upon request] [IEEE link]

  25. Robust Bayesian matrix factorization
    Balaji Lakshminarayanan, Guillaume Bouchard, and Cedric Archambeau
    AISTATS, 2011
    [revised pdf] [code available upon request]
    Note: the updates for a_n, c_m were wrong in the original version of the pdf. The increments ought to be ell_n and ell_m respectively instead of 1.

  26. Probabilistic models for classification of bioacoustic data
    Balaji Lakshminarayanan
    M.S. thesis, Oregon State University, 2010

  27. Non-negative matrix factorization for parameter estimation in Hidden Markov models
    Balaji Lakshminarayanan and Raviv Raich
    MLSP, 2010
    [pdf] [IEEE link]

  28. A syllable-level probabilistic framework for bird species identification
    Balaji Lakshminarayanan, Raviv Raich and Xiaoli Z. Fern
    ICMLA, 2009
    [pdf] [IEEE link]

Copyright notice: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. Personal use of this material is permitted. Permission must be obtained from the copyright holder for all other uses.


About me


Industry Experience

Academic Activities