Research Interest
My research interest lies in machine learning, Bayesian
statistics, and their applications in various scientific and engineering
disciplines — such as computational biology
and computational materials science. I
address critical computational and statistical challenges associated
with massive data analysis, helping the study of complex
biological, social, and synthetic systems. To this end, I design relational,
sparse, and nonparametric Bayesian graphical models driven by various
applications, and develop scalable Bayesian inference
algorithms for these models.
Brief Bio
I obtained PhD from MIT in 2005 and worked as a postdoctoral
researcher at MIT from 2005 to 2007. I joined Purdue university
in 2007 and was tenured in 2013. I received
the A. Richard Newton Breakthrough Research Award from Microsoft
Research in 2008, the Interdisciplinary Award from Purdue University in
2010, and the NSF CAREER award in 2011.
To Applicants
If you are interested in joining my group and have passion in machine learning/statistics
with a solid background in probability, linear algebra and/or
optimization, welcome to contact me via email. Please
attach your CV in your email.
Professional service
Action Editor of Journal of
Machine Learning Research
News
- Here are some
slides of my recent talks:
- Learning Gaussian
process models from big data, University of Cambridge,
2012.
It covers my recent work on Bayesian tensor
decomposition, nonparametric stochastic blockmodels, and EigenGPs
(where GP meets PCA).
-
Bayesian learning with big
data, UCL, 2012.
It covers Bayesian online learning (virtual vector machine)
and EigenGP.
-
Scalable
Bayesian learning for complex data, CSE of Georgia Institute
of Technology, 2011. It covers EigenNet (selecting correlated variables), virtual vector machine,
and parallel inference of LDA on GPUs.
Recent papers:
-
Joint network and node selection for pathway-based genomic data analysis,
Shandian Zhe, Syed A.Z. Naqvi, Yifan Yang, and Yuan Qi, accepted by Bioinformatics, 2013.
-
Message Passing with relaxed moment matching, Y. Qi, Y. Guo, ICML,
2013
-
Distributed Autonomous Online Learning: Regrets and Intrinsic Privacy-Preserving Properties,
F. Yan, S. Sundaram, S. V. N. Vishwanathan, and Y. Qi,
Accepted for publication, IEEE Transactions on Knowledge and Data Engineering, 2012.
-
Self-adjusting Models for Semi-supervised Learning in Partially-observed Settings,
F. Akova, B. Rajwa, Y. Qi, and M. Dundar,
IEEE International Conference on Data Mining, 2012.
- Using Probabilistic Generative Models For Ranking Risks of Android Apps, H. Peng, C. Gates, B.
Sarma, N. Li, Y. Qi, R. Potharaju, C. Nita-Rotaru and I. Molloy,
ACM Conference on Computer and Communications Security, Oct., 2012. [pdf]
- Minimizing Private Data Disclosures in the Smart Grid,
W. Yang, N. Li, Y. Qi, W. Qardaji, S. McLaughlin and P. McDaniel,
ACM Conference on Computer and Communications Security, Oct., 2012. [pdf]
- Infinite Tucker decomposition: nonparametric Bayesian models for multiway data analysis,
Z. Xu, F. Yan, Y. Qi, Proceedings of ICML, 2012. [pdf]
- Bayesian nonexhaustive learning for online discovery and modeling of emerging classes,
M. Dundar, F Akova, Y. Qi, B. Rajwa, Proceedings of ICML, 2012. [pdf]
-
My postdoc Zenglin Xu and I gave a
tutorial on Probabilistic Matrix and Tensor models for Network and
Multiway Data Analysis at
AAAI 2012
Our research is featured in Marketwatch news
report and the August 2012 issue of
Drug Development &
Discovery magazine. The article
"Bringing Stem Cells to the Forefront" describes the
work of my group
on Bayesian analysis of massive cytometric data
on a supercomputer for rare cancer stem cell
identification.
Our group co-organized the workshop of Machine Learning for
Social Computing at NIPS 2010.
|
|
- Associate Professor
- Department of Computer Science
- Department of Statistics
- Department of Biology (by courtesy)
- Purdue University
|