I am a networking researcher at
Microsoft Research Redmond and the
Office of the CTO, Azure for Operators.
My research interests span:
- practical reinforcement learning (RL) for networking
- video systems (streaming, conferencing, etc.)
- transport and application layers
I completed my Ph.D. in computer science at Stanford University, advised by
Keith Winstein and
Philip Levis.
My dissertation was
on the development of platforms and algorithms to achieve
practical RL on the
internet, in the context of video streaming and congestion control.
My work has received the
IRTF Applied Networking Research Prize,
USENIX NSDI Community Award, and
USENIX ATC Best Paper Award. I am the creator of
Puffer, a live-streaming site
that has reached more than 200,000 users.
Before that, I graduated from Tsinghua University, where I received
a B.S. in computer science from
Yao Class and a B.A. in economics. I also studied at MIT in 2014.
I tweet research internship opportunities and bad jokes.
Zhengxu Xia*, Yajie Zhou*, Francis Y. Yan, Junchen Jiang (*equal contribution)
ACM SIGCOMM, August 2022
menu details
Genet is a novel training framework that enhances the performance and
generalization of reinforcement learning (RL) algorithms in networking.
Genet builds on curriculum learning with judicious use of rule-based baselines.
It substantially improves the performance and generalization of simulation-trained
RL algorithms under unseen workloads and in real environments.
Jeongyoon Eo, Zhixiong Niu, Wenxue Cheng, Francis Y. Yan,
Rui Gao, Jorina Kardhashi, Scott Inglis, Michael Revow, Byung-Gon Chun,
Peng Cheng, Yongqiang Xiong
Asia-Pacific Workshop on Networking (APNet), July 2022
menu details
OpenNetLab is an open platform for
training, validating, and evaluating RL-based congestion-control
(bandwidth estimation) algorithms for real-time communications (RTC) such as
videoconferencing. It has successfully aided the development of novel RL-based
congestion-control algorithms for RTC during our
Grand Challenge
hosted at ACM MMSys '21.
Zhiying Xu, Francis Y. Yan, Rachee Singh, Justin T. Chiu, Alexander M. Rush, Minlan Yu
arXiv:2210.13763 (preprint), October 2022
menu details
Teal is a deep learning-based traffic engineering (TE) scheme that
accelerated the TE optimization on large WANs by several orders of magnitude
while achieving near-optimal traffic allocation.
Michael Rudow, Francis Y. Yan, Abhishek Kumar, Ganesh Ananthanarayanan,
Martin Ellis, K.V. Rashmi
In submission
menu details
Tambur is a new approach to forward error correction (FEC) for
videoconferencing built upon streaming codes and machine learning.
Tambur reduced decoding failures while consuming less bandwidth for redundancy.
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),
February 2020
menu details
We built
Puffer, 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
menu details
Pantheon is a “training
ground” for congestion-control research and has
assisted four schemes from other research groups in publishing at
NSDI 2018
(
Copa and
Vivace),
ICML 2019
(
Aurora),
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.
