IEEE Talk: The Last Wireless Algorithms Designed by Humans

#communications #machine-learning

Cell-edge rate is how next-generation networks get judged, and almost none of the utilities we actually optimize target it. Percentile programs do. They are also non-convex, non-smooth and strongly NP-hard. This talk follows that one problem across four papers, and at each step there is less of the algorithm left for a person to design.

It begins with sum-least-q-th-percentile rate maximization, which puts the fraction of users you care about directly into the objective and recovers max-min and sum-rate at its two ends. Two fractional transforms make it block-concave, giving cyclic algorithms that reach stationary points orders of magnitude faster than SCA or SQP, and the same idea carries over to MU-MIMO beamforming through a somewhat unexpected equivalence with a percentile-WMSE problem. Work in progress moves all of this to cell-free massive MIMO, where coherent joint transmission breaks the concavity and a change of variables puts it back.

Then the solver goes away. A neural network trained directly on the non-smooth utility, differentiating through the sort itself, matches the optimum where one is known and runs three to four orders of magnitude faster.

Then the designer goes away too! Given an immutable evaluator and a page of instructions, an AI agent ran eighty-one experiments over twenty-six hours and came back with a model within half a percent of the best solver we have, at roughly 600× lower inference cost, and with a small theorem attached: the parameterization it found is exactly max-min optimal at the minimum percentile, whatever the weights turn out to be.

I will close on what is left for us to do, and the path forward for us as wireless researchers.

Ahmad Khan (M’IEEE) received the Ph.D. and M.A.Sc. degrees from the Department of Electrical and Computer Engineering at the University of Toronto, Canada, in 2023 and 2017, respectively, and the B.S. degree in Electrical Engineering with First Class Honours from King Fahd University of Petroleum & Minerals (KFUPM), Dhahran, Saudi Arabia, in 2015. During his graduate studies, he was awarded the Edward S. Rogers Fellowship, the Wallberg Memorial Fellowship, the Ontario Graduate Scholarship, and the Queen Elizabeth II Graduate Scholarship in Science and Technology.

In 2021, he joined Ericsson Ottawa as a Machine Learning Engineer, and since 2023 has held a dual role there as Project Manager and Research Scientist in AI RAN R&D. In 2024, he was a visiting researcher at Ericsson Research in Stockholm, Sweden, and is an alumnus of the company’s prestigious Early Career Program. He also holds a patent in wireless resource management.

His research interests include wireless resource management — specifically beamforming and scheduling — and applied machine learning for next-generation wireless networks. He has published in IEEE Transactions on Signal Processing, including a two-part paper, IEEE Transactions on Communications, IEEE Transactions on Wireless Communications, IEEE Signal Processing Letters, IEEE GLOBECOM, and IEEE Access, among others. His work spans collaborations with academic institutions including Yale University and he also supervises graduate students and postdoctoral researchers at the University of Toronto through a funded research collaboration between Ericsson and the university.

• Add Event to Calendar
  iCal
  Google Calendar

Loading virtual attendance info...

• 19 Union St
• Kingston, Ontario
• Canada K7L 3N9
• Building: Walter Light Hall
• Room Number: 314

---

• Contact Event Hosts

• Starts 30 September 2026 04:00 AM UTC
• Ends 21 October 2026 04:00 PM UTC
• No Admission Charge

•