I am a first year Ph.D. student in the Department of Computer Science at the University of Toronto, supervised by Chris Maddison and Murat Erdogdu. Previously, I did my M.Sc. degree in the Department of Mathematics and Statistics at McGill University under the supervision of David Stephens. Before that, I did my B.Sc. degree in Honours Mathematics and Computer Science at McGill University.
My goal is to develop and refine the computational and statistical tools needed to build agents and systems that make optimal decisions under uncertainty. On the computational side, I have focused on gradient-based stochastic optimization and sampling algorithms. On the statistical side, I am currently exploring how the use of intermediate data representations can improve our ability to process and exploit data for optimal decision making.
Papers
Adaptive Importance Sampling for Finite-Sum
Optimization and Sampling with Decreasing Step-Sizes.
Ayoub El Hanchi, David A. Stephens
Advances in Neural Information Processing Systems, 2020
paper
Working papers
Stochastic Reweighted Gradient Descent.
Ayoub El Hanchi, David A. Stephens
paper
A Lyapunov Analysis of Loopless SARAH.
Ayoub El Hanchi
paper
Thesis
Large Scale Optimization and Sampling for Machine Learning and Statistics.
M.Sc. in Mathematics and Statistics, McGill University, May 2021.
thesis