Ilyas Fatkhullin
Postdoctoral Scholar at Stanford University
Curriculum Vitae
Google Scholar
About
I am a Postdoctoral Scholar in the Department of Management Science and Engineering at Stanford University, mentored by Prof. Renyuan Xu and Prof. Madeleine Udell. I completed my Ph.D. in Computer Science at ETH Zurich in September 2026, where I was an ETH AI Center Fellow advised by Prof. Niao He. My dissertation, Structure, Geometry, and Noise in Stochastic First-Order Optimization, brings together my work on theoretically grounded algorithms for machine learning and optimization, with an emphasis on data efficiency, scalability, and safety. Previously, I worked with Prof. Boris Polyak on control theory and with Prof. Peter Richtárik on communication-efficient distributed training.
My research contributions have appeared in leading machine learning venues including NeurIPS, ICML, AISTATS, Journal of Machine Learning Research, as well as SIAM Journal on Optimization, SIAM Journal on Control and Optimization.
My postdoctoral research at Stanford is supported by a Swiss National Science Foundation (SNSF) Postdoc.Mobility Fellowship for the project Structure Exploiting Optimization for Data-Efficient Reinforcement Learning and Games. I previously received the ETH AI Center Doctoral Fellowship and a DAAD Scholarship for my master’s studies in Germany.
Research Overview
My work centers on three interconnected pillars that address fundamental challenges in modern machine learning:
🔬 Non-convex Optimization: I develop rigorous mathematical frameworks to understand complex optimization landscapes, including hidden convexity structures that enable global solutions to seemingly intractable non-convex problems.
⚡ Data Efficiency and Robustness: I design robust algorithms that maintain performance under challenging statistical conditions, such as heavy-tailed noise and limited data scenarios, with particular relevance for policy gradient methods in reinforcement learning.
🚀 Scalable Systems: I create communication-efficient distributed training algorithms that enable large-scale machine learning while preserving theoretical guarantees, including the popular EF21 algorithm.
News
- November 2026 – I will be attending the 2026 INFORMS Annual Meeting in San Francisco, California (November 1-4, 2026).
- October 2026 – Joined the Department of Management Science and Engineering at Stanford University as a Postdoctoral Scholar, working with Prof. Renyuan Xu and Prof. Madeleine Udell.
- September 2026 – Completed my Ph.D. in Computer Science at ETH Zurich. My dissertation is titled Structure, Geometry, and Noise in Stochastic First-Order Optimization.
- August 2026 – We are organizing the Swiss Optimization Symposium, an exciting workshop taking place at Monte Verità in Ascona, Switzerland (August 23-27, 2026).
- June 2026 – Awarded a Swiss National Science Foundation (SNSF) Postdoc.Mobility Fellowship for the project Structure Exploiting Optimization for Data-Efficient Reinforcement Learning and Games at Stanford University.
- June 2026 - Attended the SIAM Conference on Optimization (OP26) in Edinburgh, United Kingdom (June 2-5), as a minisymposium organizer and invited speaker.
- May 2026 – Attended the ELLIIT symposium and focus period on Optimization for Learning in Lund, Sweden (Invited Visiting Scholar).
- March 2026 – Attended INFORMS IOS in Atlanta, U.S.A., as a Session organizer and speaker.
- February 2026 – Finished a 5-month internship at Amazon as Applied Scientist Intern.
- December 2025 – Presented “Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity.” at NeurIPS Workshop on Constrained Optimization for Machine Learning. Oral Presentation Award for the best fundamental (theoretical or algorithmic) contribution.
- October 2025 – Started an Applied Scientist internship with Amazon’s Forecasting & Optimization team in Luxembourg, focusing on large-scale capacity management problems across the delivery network.
- August 2025 – Delivered “Can SGD Handle Heavy-Tailed Noise?” at the H. Milton Stewart School of Industrial and Systems Engineering (Georgia Tech) student seminar in Atlanta.
- July 2025 – Attended the International Conference on Continuous Optimization ICCOPT 2025 at the University of Southern California in Los Angeles, USA, and presented “Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence.”
- July 2025 – Attended the International Conference on Stochastic Programming (ICSP) 2025 in Paris, France, and presented “Safe-EF: Error Feedback for Nonsmooth Constrained Optimization (with Applications to Humanoid Fleet Training).”
- March 2025 – Research visit at Georgia Tech’s H. Milton Stewart School of ISyE with Prof. Guanghui (George) Lan.