I like methods that are simple but not superficial, effective but not sophisticated, generative but not with degenerated performance.
I am a
first second year Ph.D. student in Machine Learning Department in Carnegie Mellon University. My research interests center around applying machine learning and optimization techniques to real-life challenges and seeing how these methods can be improved.
I have research experiences in pattern recognition, dynamic control systems, and approximation algorithms.
I have a solid background in math, control, and artificial intelligence. I maintained the best overall GPA (93.4 on a 100 scale) among 170 students in department of Automation by the time of graduate school application. In addition, I received a 94% percentile ranking in the GRE Math Subject test whose body of test-takers is primarily math-major students. I was also one of the 11 students who fulfilled a dual major in Mathematics in a class of 3000+ students.
Department of Automation in Tsinghua University focuses on designing autonomous systems for manufacturing industries and robotics. It has sub-disciplines in Control Theory and Engineering, Pattern Recognition and Intelligent Systems, Systems Engineering, Measurement and Automatic Devices, Navigation, Guidance and Control, Enterprise Information Systems and Engineering, and Bioinformatics.
Ph.D. student in Machine Learning Dept., School of Computer Science, Carnegie Mellon University, 8/2011-now.
- Advised by Professor Jeff Schneider.
B.S. in Automation (EECS), Dual B.S. in Mathematics, Tsinghua University, 8/2007-7/2011.
- 1st GPA in Automation by the time of graduate school application.
- GRE Math Subject Test (whose testee body is math major students): 94%.
- Totally 11 students dual majored in Mathematics in a class of 3000+ students.
Exchange Study (Credits Transferred), Georgia Inst. of Technology, 8/2009-12/2009.
- Only 6 students from applicants university-wide were given this course-based study opportunity.
- Yifei Ma, Li Li, Xiaolin Huang, Shuning Wang, Robust Support Vector Machine Using Least Median Loss Penalty, Proceedings of the 18th IFAC World Congress, Volume 18, Part 1, 2011.
9/2011-current (Machine Learning) Visualization and Classification for Astronomical Object Spectra.
Independent, supervised by Prof. Jeff Schneider, Machine Learning Department, Carnegie Mellon University.
- Fetched spectra data from NASA SDSS dataset (www.sdss.org) with python+sqlite scripts.
- Performed supervised classification for 8 star classes with various methods and achieved an accuracy of 88%.
- Working on look-ahead heuristics for label querying in the hope of decreasing the sample complexity.
[Poster] [Report] [Slides]
3/2011-6/2011 (Theoretical Computer Science) Primal-Dual Approximation Algorithms and Their Applications.
Independent, B.S. thesis project, supervised by Professor Zhenbo Wang, Math Dept., Tsinghua University.
- Designed unified framework and program implementation of primal-dual approximation algorithms that bound NP-hard problems in P time.
7/2010-6/2011 (Pattern Recognition) Robust Classification under Least Median Criteria. [publication]
Independent, B.S. thesis project, supervised by Professor Li Li, Inst. of Systems Eng., Tsinghua University.
- Developed a new robust classification method (Median Loss-SVM) via modified Least Median Regression.
- Derived a Lagrangian dual representation of Median Loss-SVM via Karush-Kuhn-Tucker conditions.
- Compared Median Loss-SVM with recent robust-SVM methods on nonlinear benchmark data sets.
1/2010-6/2010 (Control Theory) Stability Analysis of Continuous Switching Cone-wise Linear Systems.
Independent, supervised by Professor Shuning Wang, Inst. of Systems Eng., Tsinghua University.
- Discovered a set of solvable smoothly connected differential equations with special features.
- Designed an iterative local search algorithm, inspired by Markov Chain Monte Carlo I learnt in a graduate AI course.
- The above solutions represented new conditions for analysis with minor extensions of recent works.
9/2010-10/2010 (AI and GUI) Graphic Card Game (a Variation on the MS 'Hearts') with AI Agent Design.
In group of 2 students, supervised by Professor Changshui Zhang, Dept. of Automation, Tsinghua University.
- My job was to develop the UI and an AI dynamic programming strategy based on the 2-player α-β tree.
8/2009-12/2009 (Embedded Systems) Design of Embedded Application with Serial Peripheral Interface.
Independent, supervised by Professor John Peatman, Dept. of ECE, Georgia Institute of Technology.
- Designed a device to measure the initial height of a free fall by timing the duration of weightlessness.
- Developed power supply, hardware data link and microcontroller program to integrate an accelerometer on a different voltage level. [report]
5/2009-6/2009 (Java Software) English Vocabulary Builder with Novel Design of Efficient Repetition Cycles.
Independent, supervised by Professor Li Zheng, Dept. of Computer Science, Tsinghua University.
- Used TCP congestion control principles to repetition cycle design and improved my GRE test preparation.
2/2009-6/2009 (Data Structure) k-d Search Tree for Dense Two-Dimensional Data.
Independent, supervised by Professor Junhui Deng, Dept. of Computer Science, Tsinghua University.
- Developed a k-d tree with modification on tree depth limit and an additional box shrink strategy for scalability.
- Ranked top in an in-class competition for algorithm runtime.
|Machine Learning||Intermediate Statistics|
|Machine Learning Journal Club|
|Differential Geometry||Probability and Statistics|
|Probability Theory (1)||Mathematical Modeling|
|Mathematical Analysis||Measures and Integrals|
|Advanced Algebra and Geometry||Mathematical Statistics|
|Differential Equations (1)||Applied Stochastic Processes|
|C++ Programming||Numerical Analysis|
|JAVA and Object Oriented Programming||Operations Research|
|Computer Communications||Intelligent Optimization Algorithms|
|Automatic Control Theory||Introduction to Artificial Intelligence|
|Introduction to Digital Signal Processing||Fundamental Pattern Recognition|
|Introduction to Systems Engineering||Fundamentals of System Identification|
|General Physics||Embedded Micro-controller Design|
|Digital Electronics (with FPGA)||Power Electronics|
|Fundamentals of Analog Electronics||Electromechanical and Electromagnetic Energy Conversion|
Honors and Awards
2007-2010, 1st Level Academic Scholarship every year in Tsinghua University;
10/2009, 31/700 in IEEEXtreme 24-Hour Programming Competition (team leader);
10/2006, 1st prize in National High School Physics Competition;
03/2006, Qualified for the American Invitational Mathematics Examination (no further award for foreigners);
10/2004, 1st prize in National High School Math Competition (over 2 years younger than most others).
Standardized Test Scores
10/2010 TOEFL 114/120 (speaking 26/30, reading 30/30, listening 30/30, writing 28/30);
12/2009 GRE verbal 580/800 (82%), quantitative 800/800 (94%), writing 4.5/6 (67%);
11/2010 GRE math subject test 870/990 (94%).
- Joined student volunteer group for over 10 years;
- Served as a regular campus guide for visitors in Tsinghua University;
- Volunteered for the 2008 Beijing Olympic Games (in medal ceremonies as a winning national flag raiser).
STUDENT ACTIVITIES AND HOBBIES
- Editor for Tsinghua Student Psychology Club Journal;
- Member of Campus Tour Guide Association;
- Member of Tsinghua Honor Guard (to display and escort the national flag on ceremonial occasions);
- Volunteer teaching assistant for 30 students on Fundamentals of Analog Electronics and Data Structure;
- Classical Chinese Philosophy like the Analects (Confucius) and Tao Te Qing (Lao-tzu);
- Piano, swimming, and running.