top of page

Stay curious.

Research

Statistical Learning of Complex Networked Systems

Complex systems consist of heterogeneous agents mutually influenced via interactions of different intensities over multiple spatio-temporal scales. To understand and control these complex systems, the network theory, satistical physics and statistical machine learning theory provide an elegant handler to unveil the interesting properties and dynamics of the complex networked system.                                  

                                                   

 

Compact yet Accurate Statistical Model Learning for Complex Dynamics of Cyber-Physical Systems

We surrounded by a physical world that is hopeless complicated. Their understanding, mathematical description, modeling, prediction and eventually control pose the major challenges for the construction of intelligent Cyber-Physical Systems (CPS). We address this challenge by combining the statistical and causal inference approaches with state-of-art machine learning techniques, which enables capturing their mathematical structures and physical natures via compact yet accurate models

 

                                                

Ultra-fast and Evolvable Computing Engine for Personalized Medicine

Personalized medicine aims to be predictive, personalized, preventative and participatory by using information from genomes and their derivatives (such as proteins and metabolites) to guide medical decision-making. As an exascale Big-data application, the translational analysis of personal biological measurements go far beyond the current computing paradigms. Our research aims to provide an automated top-down computing engine synthesis flow built upon our state-of-art applicaiton profiling frameworks to provide 1000x runtime improvement. 

                                               

 

                                                 

SERVICES

ABOUT ME

Thanks for your footprint here ! 

 

My name is Yuankun Xue. I am currently a PhD candidate (update: I have successfully defended!) at Unversity of Southern California working with Professor Paul Bogdan. Before I joined USC, I obtained my B.Sc and M.Sc (with highest honor) at Fudan University in China in 2011 and 2014, respectively. My research interests mainly focus on Statistical machine learning, Beyasian inference, Causal inference,  Time-series analysis, Complex network analysis. I am also the co-founder of YHgenomics, a precise medicine startup based on Chengdu, China.

ABOUT

Publication

Conference

PROJECTS

Publication

Conference & Journals

CONTACT

USC Office

3740 McClintock Avenue​

Los Angeles, CA 90089

 

yuankunx@usc.edu

Success! Message received.

YHgenomics Office

Building 1 Tianhe Biological Science and Technology Park,

Chengdu, Sichuan Province 610017

China

www.yhgenomics.com

yuankun@yhgenomics.com

  • LinkedIn - Grey Circle
Employment

To apply for a job with YHgenomics, please visit yhgenomics.com

CLIENTS
CONTACT

© 2016 by Yuankun Xue

bottom of page