| |
| |
|
 |
| Jingu Kim |
Ph.D.
Senior research engineer at Netflix |
Email : x at y where (x = jingu.kim, y = gmail.com)
Address : San Jose, CA
Quick Links:
|
|
| |
|
| |
| |
| |
| About Me |
| |
I am a senior research engineer at Netflix working on machine learning and recommendation systems. Before that, I worked as a senior researcher at Nokia analyzing mobile user data and developing predictive machine learning algorithms. I received M.S. and Ph.D. in Computer Science from the College of Computing at Georgia Tech, where I also worked as a postdoc. I was advised by Haesun Park, with whom I worked on exciting research problems in machine learning and numerical methods. I was an intern researcher at Microsoft Research Redmond with Bo Thiesson in 2010. Before coming to Georgia Tech, I spent one year at the Imaging Media Research Center of the Korea Institute of Science and Technology after completing my B.S. in Computer Science and Engineering at Seoul National University.
|
| Curriculum vitae: [PDF] |
| |
| Areas of research interest: |
|
- Machine learning, statistical modeling, data mining |
| - Recommendation systems |
| - Numerical optimization, distributed optimization, computational statistics in massive scale |
|
|
|
| |
| |
| Publications |
| |
2015
- Simultaneous Discovery of Common and Discriminative Topics via Joint Nonnegative Matrix Factorization.
Hannah Kim, Jaegul Choo, Jingu Kim, Chandan Reddy, and Haesun Park
In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), pp. 567-576, 2015.
[URL]
2014
- Conditional Log-linear Models for Mobile Application Usage Prediction.
Jingu Kim and Taneli Mielikäinen.
In Proceedings of the 2014 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), LNCS Volume 8724, pp. 672-687, 2014.
[PDF] [URL]
- Algorithms for Nonnegative Matrix and Tensor Factorizations: A Unified View Based on Block Coordinate Descent Framework.
Jingu Kim, Yunlong He, and Haesun Park.
Journal of Global Optimization, 58(2), pp. 285-319, 2014.
[PDF] [URL]
2013
- Regularization Paths for Sparse Nonnegative Least Squares Problems with Applications to Life Cycle Assessment Tree Discovery.
Jingu Kim, Naren Ramakrishnan, Manish Marwah, Amip Shah, and Haesun Park.
In Proceedings of the 2013 Thirteenth IEEE International Conference on Data Mining (ICDM), pp. 360-369, 2013.
[PDF]
2012
- Command Generation Techniques for a Pin Array Using the SVD and the SNMF.
Ryder C. Winck, Jingu Kim, Wayne J. Book, and Haesun Park.
In Proceedings of the 10th IFAC Symposium on Robot Control (SYROCO), Dubrovnik, Croatia, 2012
- A Control Loop Structure Based on Semi-Nonnegative Matrix Factorization for Input-Coupled Systems.
Ryder C. Winck, Jingu Kim, Wayne J. Book, and Haesun Park.
In Proceedings of the 2012 American Control Conference (ACC), Montreal, Canada, 2012
- Group Sparsity in Nonnegative Matrix Factorization.
Jingu Kim, Renato Monteiro, and Haesun Park.
In Proceedings of the 2012 SIAM International Conference on Data Mining (SDM), pp. 851-862, 2012
[PDF]
- Fast Variational Mode-Seeking.
Bo Thiesson and Jingu Kim.
In Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics (AISTATS) 2012, JMLR: W&CP 22, pp. 1230-1242, La Palma, Canary Islands, Apr. 21-23, 2012.
[PDF]
- Fast Nonnegative Tensor Factorization with an Active-set-like Method.
Jingu Kim and Haesun Park.
In High-Performance Scientific Computing: Algorithms and Applications, Springer, pp. 311-326, 2012.
[PDF] [URL] [SOFTWARE]
2011
- Nonnegative Matrix and Tensor Factorizations, Least Squares Problems, and Applications.
Jingu Kim.
Ph.D. Thesis, Georgia Institute of Technology, 2011.
[PDF] [URL]
- Fast Nonnegative Matrix Factorization: An Active-set-like Method And Comparisons.
Jingu Kim and Haesun Park.
SIAM Journal on Scientific Computing (SISC), 33(6), pp. 3261-3281, 2011.
[PDF] [URL] [SOFTWARE]
- Statistical Optimization of Non-Negative Matrix Factorization.
Anoop Korattikara, Levi Boyles, Max Welling, Jingu Kim, and Haesun Park.
In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (AISTATS) 2011, JMLR: W&CP 15, pp. 128-136, Fort Lauderdale, FL, USA, Apr. 11-13, 2011.
[PDF]
- Sparse Nonnegative Matrix Factorization for Protein Sequence Motif Discovery.
Wooyoung Kim, Bernard Chen, Jingu Kim, Yi Pan, and Haesun Park.
Expert Systems with Applications, 38(10), pp. 13198-13207, 2011.
[URL]
2010
- Supervised Raman Spectra Estimation based on Nonnegative Rank Deficient Least Squares.
Barry Drake, Jingu Kim, Mahendra Mallick, and Haesun Park.
In Proceedings of the Thirteenth International Conference on Information Fusion, Edinburgh, UK , 2010.
[PDF]
- Fast Active-set-type Algorithms for L1-regularized Linear Regression.
Jingu Kim and Haesun Park.
In Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS) 2010, JMLR: W&CP 9, pp 397-404, Chia Laguna, Sardinia, Italy, May 13-15, 2010.
[PDF] [POSTER]
2008
- Toward Faster Nonnegative Matrix Factorization: A New Algorithm and Comparisons.
Jingu Kim and Haesun Park.
In Proceedings of the 2008 Eighth IEEE International Conference on Data Mining (ICDM), pp. 353-362, 2008.
[PDF] [SLIDES] [SOFTWARE]
- Sparse Nonnegative Matrix Factorization for Clustering.
Jingu Kim and Haesun Park.
Georgia Tech Technical Report GT-CSE-08-01, 2008.
[PDF]
|
| |
| |
| |
| Course Work |
| |
|
|
| |
| |
| |
| Personal |
| |
I enjoy swimming, running, tennis, and snowbording. When I completed a half marathon, my record was within top 20 percent (1hr 45min) of all participants. I used to enjoy lindy hop(swing dance) as well. When I am lucky to have a longer break, I like traveling beautiful places. I used to enjoy birdwatching around riversides or wetlands.
|
 |
|
| |
| |
| |
| Last updated in January 2015 |
|
|
|
| |
| |
|
| Back to Top |
| |
| |
| |
| Nonnegative Matrix and Tensor Factorizations |
| |
| This section provides implementations of efficient nonnegative matrix factorization (NMF) and nonnegative tensor factorization (NTF) algorithms described in the following papers. The NTF algorithms are for the nonnegative Candecomp/PARAFAC (NCP) model. A key subroutine is a fast algorithm for nonnegativity-constrained least squares problem, which maybe of interest to many applications other than NMF or NTF. Please email to Jingu Kim with any questions in using the code, bug reports, or comments. |
| |
| MATLAB code |
| |
- See Github page or download as zip.
- Plain, regularized, and sparse NMFs are all included.
- To use nonnegative tensor factorization, installation of MATLAB Tensor Toolbox is required. The version of the toolbox with which this software was tested is 2.4.
- Earlier files: NMF and NTF (no longer maintained).
|
| |
| Python code |
| |
|
|
| |
| Related papers |
| |
- Fast Nonnegative Matrix Factorization: An Active-set-like Method And Comparisons.
Jingu Kim and Haesun Park.
SIAM Journal on Scientific Computing (SISC), 33(6), pp. 3261-3281, 2011
[PDF]
- Algorithms for Nonnegative Matrix and Tensor Factorizations: A Unified View Based on Block Coordinate Descent Framework.
Jingu Kim, Yunlong He, and Haesun Park.
Journal of Global Optimization, 58(2), pp. 285-319, 2014.
[PDF] [URL]
- Fast Nonnegative Tensor Factorization with an Active-set-like Method.
Jingu Kim and Haesun Park.
In High-Performance Scientific Computing: Algorithms and Applications, Springer, pp. 311-326, 2012.
[PDF] [URL]
|
| |
| |
|
|
|
