I am a Senior Researcher
Mobility and Networking Research Group at
Microsoft Research Redmond
Office of the CTO, Azure for Operators.
My research focuses on practical machine learning (ML) for networking,
seeking to create ML algorithms that are deployable on real-world networked systems
and build platforms for training and evaluating novel algorithms.
I completed my Ph.D. in computer science at Stanford University, advised by
Keith Winstein and
My dissertation was
on the development of platforms and algorithms to achieve
practical reinforcement learning (RL) on the
Internet, in the context of video streaming and congestion control.
My work has received the Applied Networking Research Prize, the USENIX NSDI
Community Award, and the USENIX ATC
Best Paper Award.
Before that, I graduated from Tsinghua University, where I received
a B.S. in computer science from
Yao Class (founded by Turing Award laureate
Andrew Chi-Chih Yao)
and a B.A. in economics. I also studied at MIT in 2014.
Here is my CV.
Prospective students: Please reach out if you are interested in a
collaboration on ML/RL for systems and networking.
I am also hiring research interns:
For students physically located in the United States or Canada, please apply
For students physically located in China, please apply
and select the project
“Learning Bandwidth Estimation for Real-Time Video.”
Please send me an email with your resume after submitting your application.
Francis Y. Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong,
Keyi Zhang, Philip Levis, Keith Winstein
USENIX Symposium on Networked Systems Design and Implementation (NSDI),
, a free, publicly
accessible website that live-streams television channels and operates as a
randomized experiment of adaptive bitrate (ABR) algorithms.
As of June 2020, Puffer has attracted 120,000 real users and streamed 60 years
of video across the Internet. Using Puffer, we developed an ML-based ABR algorithm,
Fugu, that robustly outperformed existing schemes by learning in situ
on real data from its actual deployment environment.
Francis Y. Yan, Jestin Ma, Greg D. Hill, Deepti Raghavan, Riad S. Wahby,
Philip Levis, Keith Winstein
USENIX Annual Technical Conference (ATC), July 2018
is a community “training
ground” for Internet congestion-control research and has
assisted four schemes from other research groups in publishing at
and SIGCOMM 2020 (TCP-TACK
It also enabled our own ML-based
congestion-control algorithm, Indigo, which was trained to imitate expert
congestion-control algorithms we created in emulation
and achieved good performance over the real Internet.