Ilyas Fatkhullin
Postdoctoral Scholar at Stanford University
Curriculum Vitae
Google Scholar
About
I am an incoming Assistant Professor in the Department of Mathematics at the London School of Economics and Political Science (LSE), starting in 2027. I will be recruiting Ph.D. students for Fall 2027.
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. Previously, I worked with Prof. Boris Polyak on control theory, Prof. Guanghui (George) Lan on functional constrained optimization, and 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 competitive Swiss National Science Foundation (SNSF) Postdoc.Mobility Fellowship. I previously received the ETH AI Center Doctoral Fellowship for my Ph.D. studies in Switzerland and a DAAD Scholarship for my master’s studies in Germany.
Prospective Students
I am recruiting Ph.D. students interested in optimization, machine learning, and reinforcement learning. If you would like to join my group, please complete the prospective student interest form. See the research overview below to learn more.
Research Overview
My work centers on three interconnected pillars that address fundamental challenges in modern machine learning:
Non-convex Optimization: I develop mathematical foundations and algorithms for solving non-convex problems in learning and decision-making. My research seeks to identify exploitable structure and translate it into convergence guarantees and effective methods for increasingly complex models.
Data Efficiency and Robustness: I develop learning algorithms that make effective use of limited data and remain reliable under uncertainty. A central goal is to advance optimization and reinforcement learning methods that combine strong statistical guarantees with stable performance in practice.
Scalable Learning Systems: I design optimization methods that address the computational and communication demands of large-scale learning. My research aims to connect algorithmic efficiency with reliable performance across distributed and resource-constrained environments.
News
- December 2026 – I will be attending NeurIPS 2026 in Atlanta, Georgia (December 9–13, 2026).
- November 2026 – I attended 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, 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.
Show earlier news
- 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 as an invited visiting scholar.
- March 2026 – Attended INFORMS IOS in Atlanta, U.S.A., as a session organizer and speaker.
- February 2026 – Finished a five-month internship at Amazon as an Applied Scientist Intern.
- December 2025 – Presented “Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity” at the 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.