El Houcine Bergou

About

As of January 2019, El Houcine Bergou is a Postdoctoral Research Fellow at Extreme Computing Research Center (ECRC) in King Abdullah University of Science and Technology (KAUST), working with Professor Panagiotis Kalnis in his research group. Prior to this, he spent a year as a Postdoctoral Research Fellow in the Optimization and Machine Learning group of Professor Peter Richtárik.

Education and Early Career

Dr. Bergou has a PhD degree in numerical methods for least squares problems with application to data assimilation from the National Institute of Posts and Telecommunications (INPT) in Toulouse, France, 2014. Before joining KAUST, he was a research scientist at National Institute of Agricultural Research (INRA) in France.

Research Interest

El Houcine is focusing on numerical optimization. He’s interested in developing algorithms for continuous optimization non necessary convex problems. He has a particular focus on randomized methods.

Selected Publications

• E. Bergou, E. Gorbunov and P. Richtárik, Stochastic three points method for unconstrained smooth minimization. arXiv Preprint arXiv:1902.03591, 2019
• A. Bibi, E. Bergou, O. Sener, B. Ghanem and P. Richtárik, A stochastic derivative-free optimization method with importance sampling. arXiv Preprint arXiv:1902.01272, 2019
• E. Bergou, S. Gratton and J. Mandel, On the convergence of a non-linear ensemble Kalman smoother. Applied Numerical Mathematics 137:151-168, 2019
• E. Bergou, Y. Diouane and S. Gratton, On the use of the energy norm in trust-region and adaptive cubic regularization subproblems. 
  Computational Optimization and Applications 68(3):533–554, 2017
• E. Bergou, S. Gratton and L. N. Vicente, Levenberg-Marquardt methods based on probabilistic gradient models and inexact subproblem solution, with application to data assimilation. SIAM Journal on Uncertainties Quantification 4:924–951, 2016
• J. Mandel, E. Bergou, S. Gurol, S. Gratton and I. Kasanický, Hybrid Levenberg–Marquardt and weak constraint ensemble Kalman smoother method. Nonlinear Processes in Geophysics 23:59-73, 2016
• E. Bergou, S. Gratton and J. I. Tshimanga, The exact condition number of the truncated singular value solution of a linear ill-posed problem. SIAM Journal on Matrix Analysis and Applications 35(3):1073-1085, 2014

Education Profile

• Ph.D, Numerical methods for least squares problems with application to data assimilation, National Institute of Posts and Telecommunications (INPT), France, 2014