Research Interests
My research is in the area of video streaming and deep learning.
I'm interested in designing systems to efficiently utilize deep learning models/services and exploiting deep learning techniques to empower network systems.
I have experience in machine learning cloud services, reinforcement learning algorithms, and edge hardwares (e.g., Jetson Nano, Raspberry Pi).
|
|
Cost Effective MLaaS Federation: A Combinatorial Reinforcement Learning Approach
Shuzhao Xie,
Yuan Xue,
Yifei Zhu,
Zhi Wang
INFOCOM, 2022
paper
/
project page
/
code
As naively using multiple ML APIs can lead to lower analytical accuracy and poor user experience,
we employ reinforcement learning to select the optimal combination of MLaaSes, thus maximizing accuracy while minimizing cost.
|
|
Tencent Youtu Lab, Shanghai, China
Research Intern
Jan - May 2022
Deployed Faster-RCNN into CPU environments with C++.
Analyzed model performance under heterogeneous environments.
|
Professional Service and Teaching
|
Journal and Conference Reviewer
ICASSP 2023
|
Teaching Assistant
Big Data System (B), Tsinghua University, Fall 2021
|
Template from Jon Barron. Last updated in Sep 2023.
|
|