KAUST
2026
2025
- DSA 008, Introduction to Machine Learning (Fall 2025)
- CS 332, Federated Learning (Fall 2025)
- CS 331, Stochastic Gradient Descent Methods (Fall 2025)
- CS 398, CS Graduate Seminar (Fall 2025)
- DSA 211, Introduction to Optimization (Summer 2025)
- CS 331, Stochastic Gradient Descent Methods (Spring 2025)
2024
- CS 331, Stochastic Proximal Point Methods (Spring 2024)
2023
- DSA 006, Introduction to Machine Learning (Summer 2023)
- CS 332, Federated Learning (Spring 2023)
2022
- DSA 008, Introduction to Optimization (Fall 2022)
- CS 331, Stochastic Gradient Descent Methods (Fall 2022)
- CS 332, Federated Learning (Spring 2022)
2021
- CS 331, Stochastic Gradient Descent Methods (Fall 2021)
- CS 332, Federated Learning (Spring 2021)
2020
- CS 331, Stochastic Gradient Descent Methods (Fall 2020)
- CS 390T, Special Topics in Federated Learning (Spring 2020)
2017–2019
- CS 394D, Contemporary Topics in Machine Learning (Spring 2018, Spring 2019)
- CS 390FF, Big Data Optimization (Fall 2017, Fall 2018, Fall 2019)
University of Edinburgh
- Modern Optimization Methods for Big Data Problems (Spring 2016, Spring 2017)
- Game Theory (Fall 2010, 2011, 2012)
- Discrete Programming and Game Theory (Fall 2010, 2011, 2012)
- Optimization Methods in Finance (Spring 2012, 2013, 2014, 2015)
- Deterministic Optimization Methods in Finance (Spring 2011, 2012, 2013, 2014, 2015)
External (tutorials, schools, and invited courses)
-
Federated Optimization Tutorial (3.5 hours)
Event: Bootcamp, Simons Institute Program on Federated and Collaborative Learning, Berkeley, USA, January 26–28, 2026 -
Introduction to Machine Learning 1 and 2 (MS courses, 28 hours each)
Event: Saudi Aramco, Dhahran, Saudi Arabia, June 2023 and October–November 2025 -
The Machine Learning Summer School (invited lecturer)
Event: MLSS 2025, MBour, Senegal, June 23–July 4, 2025 -
Introduction to Optimization 1 and 2 (MS courses, 28 hours each)
Event: Saudi Aramco, Dhahran, Saudi Arabia, November 2022 and June–July 2025 -
Optimization for Machine Learning (three lectures)
Event: Applied Mathematics School, KAUST, Saudi Arabia, December 2, 2024 -
Optimization for Machine Learning (five 90 min lectures)
Event: Beijing Institute for Mathematical Sciences and Applications (BIMSA), Beijing, China, November 18–28, 2024 -
Optimization for Machine Learning (three 50 min lectures)
Event: AMCS-STAT School, KAUST, Saudi Arabia, February 25, 2024 -
Eastern European Machine Learning Summer School (lecturer)
Event: EEML 2023, Košice, Slovakia, July 9–16, 2023
slides -
1-DAV-213: Introduction to Stochastic Gradient Descent Methods (5 x 4.5 hours)
School of Mathematics, Physics and Informatics (Comenius University), Slovakia, June 20-24, 2022
Registration was handled by email. - 390015 KU VGSCO: Stochastic Gradient Descent Methods (2022S), University of Vienna, Austria, May 30-June 3, 2022
-
A Guided Walk Through the ZOO of Stochastic Gradient Descent Methods (2.5 hours)
Event: School-Conference “Approximation and Data Analysis”, Nizhny Novgorod, Russia, September 30–October 4, 2019 -
A Guided Walk Through the ZOO of Stochastic Gradient Descent Methods (5 hours)
Event: Moscow Institute of Physics and Technology, Dolgoprudny, Russia, September 28, 2019
video - A Guided Walk Through the ZOO of Stochastic Gradient Descent Methods (6 hours)
Event: ICCOPT 2019 Summer School, Berlin, Germany, August 2019
main slides, extra slides on SGD-SR and SEGA -
Randomized Optimization Methods (PhD course, 4.5 hours)
Event: Short Doctoral Course, Erwin Schrödinger International Institute for Mathematics and Physics (ESI), Vienna, Austria, February 21–22, 2019 -
Stochastic Reformulations in Linear Algebra and Optimization (2 hours)
Event: 10th Traditional Youth School Control, Information and Optimization, Voronovo, Moscow Region, Russia, June 10–15, 2018
slides 1, slides 2 -
Introduction to Optimization for Machine Learning (short outreach course, 4.5 hours)
Event: selected Saudi university students who previously participated in the Saudi National Mathematical Olympiad or IMO, KAUST, Saudi Arabia, April 25–26, 2018 -
Randomized Optimization Methods (5 hours)
Event: Data Science Summer School, CMAP, École Polytechnique, Paris, France, August 2017
slides, lecture videos: 1 2 3 4 5 -
Randomized Methods for Big Data: From Linear Systems to Optimization (tutorial)
Event: IEEE International Conference on Data Science and Advanced Analytics, Paris, France, October 19–21, 2015
slides -
Randomized Algorithms for Big Data Optimization (21 hours)
Event: Graduate School in Systems, Optimization, Control and Networks (SOCN), Université catholique de Louvain, Belgium, Fall 2015 - Optimization in Machine Learning
Event: Machine Learning Thematic Trimester, Toulouse, France, September 2015 -
Modern Convex Optimization Methods for Large-Scale Empirical Risk Minimization (tutorial, 2 hours, joint with Mark Schmidt)
Event: ICML 2015, Lille, France, July 6–11, 2015 -
Randomized Coordinate Descent for Big Data Optimization (6 hours)
Event: Khronos-Persyval Days on High-Dimensional Learning and Optimization, Grenoble, France, June 2014 -
Coordinate Descent Methods (2 hours)
Event: NATCOR PhD Course on Convex Optimization, Edinburgh, UK, June 23–27, 2014 -
Gradient Methods for Big Data (tutorial, 3 hours)
Event: Big Data: Challenges and Applications, Imperial College London, UK, February 17–19, 2014
slides