Zak Mhammedi

Zak Mhammedi

PhD Student

Australian National University

About Me

I am a fourth-year PhD student in computer science at the Australian National University, advised by Bob Williamson and Wouter Koolen.

My current research focuses on theoretical aspects of machine learning. Typical research questions I like to tackle include:

  • How well does an algorithm generalize in a given learning setting? (articles)
  • How to design (universal) algorithms that automatically adapt to different easinesses of the problem at hand? (articles)
  • To what extent can one “learn” in a given problem setting? (articles)

Interests

  • Online Learning
  • Stochastic Optimization
  • Distributionally Robust Optimization
  • Statistical Learning (Generalization Bounds)

Education

  • PhD in Computer Science

    Australian National University

  • MPhil in Computer Science, 2017

    The University of Melbourne

  • MEng in Mechanical Engineering, 2015

    The University of Melbourne

  • BSc, 2012

    Ecole Centrale Paris

Conference Papers

${}^\star$About 3% of submissions at NeurIPS receive a spotlight.

In all papers, authors are ordered according to their contribution.

Experience

 
 
 
 
 

Research Intern

Microsoft Research

Feb 2020 – Jun 2020 New York, USA
Worked and published research on a problem of continuous control with rich observations.
 
 
 
 
 

Research Intern

Centrum Wiskunde & Informatica (CWI)

Jan 2019 – Mar 2019 Amsterdam, Netherlands
Worked on developing a new and improved PAC-Bayesian generalization bound.
 
 
 
 
 

Research Visit

Centrum Wiskunde & Informatica (CWI)

May 2018 – Aug 2018 Amsterdam, Netherlands
Worked on adding Lipschitz adaptivity to certain second-order adaptive online learning algorithms.
 
 
 
 
 

Research Assistant

CSIRO

Jul 2016 – Dec 2016 Tasmania, Australia
Published research on an efficient parametrization of orthogonal recurrent neural networks.
 
 
 
 
 

Research Intern

IBM Research

Jul 2015 – Oct 2015 Melbourne, Australia
Worked on developing a model for the theoretical spread of citrus greening in Australia. Implemented the model in C++ and performed simulations.

Services

Program Commitee: COLT 2021

Reviewer: COLT 2019, COLT 2020, NeurIPS 2020, ICML 2020, JMLR

Teaching

 
 
 
 
 

Tutor

Australian National University

Aug 2017 – Oct 2018 Canberra, Australia
Taught the Information Theory course COMP2610/COMP6261.
 
 
 
 
 

Maths Tutor

Simply Maths

Oct 2013 – Oct 2014 Melbourne, Australia
Tutored secondary-level mathematics students.