More recent at the top.

  1. Accelerated stochastic matrix inversion: general theory and speeding up BFGS rules for faster second-order optimization
    RMG, Filip Hanzely, P. Richtárik and S. Stich.
    arXiv:1801.05490, 2018

  2. Learning about random media from near-surface backscattering: using machine learning to measure particle size and concentration
    Artur L. Gower, RMG, Jonathan Deakin, William J. Parnell and I. David Abrahams.
    arXiv:1801.05490, 2018

  3. Greedy stochastic algorithms for entropy-regularized optimal transport problems
    Brahim Khalil Abid and RMG.
    AISTATS 2018

  4. Tracking the gradients using the Hessian: A new look at variance reducing stochastic methods
    RMG, Nicolas Le Roux and Francis Bach.
    AISTATS 2018

  5. Randomized quasi-Newton updates are linearly convergent matrix inversion algorithms
    RMG and P. Richtárik
    SIAM Journal on Matrix Analysis and Applications , 38(4), 1380-1409, 2017

  6. Linearly Convergent Randomized Iterative Methods for Computing the Pseudoinverse
    RMG and P. Richtárik
    arXiv:1612.06255, 2016

  7. Sketch and Project: Randomized Iterative Methods for Linear Systems and Inverting Matrices
    PhD Dissertation, School of Mathematics, The University of Edinburgh, 2016

  8. Stochastic Block BFGS: Squeezing More Curvature out of Data
    RMG, D. Goldfarb and P. Richtárik
    In Proceedings of the 33rd International Conference on Machine Learning, 2016

  9. Stochastic dual ascent for solving linear systems
    RMG and P. Richtárik
    Preprint, 2015

  10. Randomized iterative methods for linear systems
    RMG and P. Richtárik
    SIAM Journal on Matrix Analysis and Applications 36(4), 1660-1690, 2015
    The 1st Most Downloaded Paper from the SIMAX website (May 2017)

  11. High order reverse automatic differentiation with emphasis on the third order
    RMG and A.L. Gower
    Mathematical Programming 155(1), 81-103, 2014

  12. Computing the sparsity pattern of Hessians using automatic differentiation,
    RMG and M.P. Mello
    ACM Transactions on Mathematical Software 40(2), 1-15, 2014

  13. A new framework for Hessian automatic differentiation
    RMG and M.P. Mello
    Optimization Methods and Software 27(2), 251-273, 2012



Technical and industrial mathematics study group reports

  1. Train Positioning Using Video Odometry
    RMG, R. Whittaker, M.D. Wykes, J. Christmas, P. Browne, J. Van lent,
    A.L. Gower and S. Ghosh
    The MIIS Eprints Archive, 2014

  2. Action constrained quasi-Newton methods (software)
    RMG and J. Gondzio
    Technical Report ERGO 14-020, 2014

  3. Conjugate Gradients: The short and painful explanation with oblique projections, 2014

  4. Hessian matrices via automatic differentiation
    R.M.Gower and M.P. Mello
    State University of Campinas technical report rp16-10 Master's thesis (despite title page, it is in English!), 2011

  5. Efficient calculation of derivatives through graph coloring
    R.M.Gower and M.P. Mello
    State University of Campinas technical report part I and part II, 2009



Sometimes I wear the hat of a reviewer

Referee for
  • Journal of Machine Learning Research
  • SIAM Journal on Scientific Computing, SIAM
  • Optimization Methods and Software, Taylor & Francis
  • Mathematical Programming Computation, Springer
  • Computational and Applied Mathematics, Springer
  • Numerical Algorithms, Springer
  • BIT Numerical Mathematics, Springer

HTML Comment Box is loading comments...