Bamdev Mishra

[+] CV

  • Low-rank factorizations for large-scale optimization algorithms:

    Here is my CV.

    The research deals with the application of manifold optimization techniques to large-scale convex optimization problems whose expected or desired solutions have low rank. We focus specifically on convex relaxations of large-scale rank-constrained problems encountered in machine learning, data reduction and bioinformatics.

    As of now, I am trying to understand this comic strip.


[+] Education and research experience

[+] Publications and codes



[+] Teaching and graduate courses

  • 2012 Sem 1: SYST003 Lab (Teaching Assistant)
  • 2011 Sem 2: Numerical Optimization (Teaching Assistant): Tutorials
  • 2011 Sem 1: Theory of Computation
  • INRIA/ENS: 2011 July: CVML Summer school
  • EECI: 2011 Feb: Optimization on Matrix Manifolds
  • SOCN: 2010 Dec: Compressed Sensing and Sparse Approximations
  • Sys017: 2010 Sem 1: Nonlinear Systems


[+] Activities

  • Actively involved in the open-source MATLAB toolbox Manopt for optimization on matrix manifolds
  • Teaching assistant at ULg
  • Created and maintained the research unit website Systmod from September 2011 to December 2013


[+] Recent updates

  • startag R3MC: A Riemannian three-factor algorithm for low-rank matrix completion [arXiv:1306.2672][Matlab code] is now accpted for publication in the proceedings of the 53rd IEEE Conference on Decision and Control. Here we show some promising results of employing the Riemannian preconditioning appoach on the low-rank manifold.

  • startag The technical report "Riemannian preconditioning" is online [arXiv:1405.6055].

    The paper exploits a basic connection between sequential quadratic programming and Riemannian gradient optimization to address the general question of selecting a metric in Riemannian optimization. The proposed method is shown to be particularly insightful and efficient in quadratic optimization with orthogonality and/or rank constraints, which covers most current applications of Riemannian optimization in matrix manifolds.

tumblr hit tracking tool