Hauptnavigation

IMG_2529-001.JPG Email: sangkyun.lee At sign cs.uni-dortmund.de
Phone: 0231/755-6490
Room-No.: OH12 R4.023

About

I'm interested in developing efficient numerical optimization algorithms for large-scale machine learning and statistical data analysis problems, focusing on non-smooth convex regularization problems.

I received my Ph.D. degree (major in optimization, minor in statistics) from the Computer Sciences Department of the University of Wisconsin-Madison, in 2011. From the same university I obtained my second master's degree in Computer Science, in 2008. I was born in South Korea, and before coming to the USA I studied in Seoul National University and received my bachelor's (summa cum laude) and my first master's degree (artificial intelligence/bioinformatics) in Computer Sciences and Engineering, in 2003 and 2005, respectively. I'm working in the Collaborative Research Center (SFB876) at TU Dortmund since August, 2011, as a postdoc researcher.
My website at University of Wisconsin-Madison link

Lectures

  • Large-Scale Optimization SoSe 2016 link
  • Numerical Optimization WiSe 2015 link
  • Large-Scale Optimization SoSe 15 link
  • Large-Scale Optimization WiSe 2014/15 link
  • Numerical Optimization SoSe 2014 link

Projects

Research Topics

Publications

Kliewer/Lee/2016a Kliewer, Viktoria and Lee, Sangkyun. EasyTCGA: An R package for easy batch downloading of TCGA data from FireBrowse. No. 4, TU Dortmund, 2016.
Lee/etal/2016a Lee, Sangkyun and Brzyski, Damian and Bogdan, Malgorzata. Fast Saddle-Point Algorithm for Generalized Dantzig Selector and FDR Control with the Ordered l1-Norm. In Arthur Gretton and Christian C. Robert (editors), Proceedings of the 19th International Conference on Artificial Intelligence and Statistics (AISTATS), pages 780--789, JMLR W&CP, 2016. Arrow Symbol
Piatkowski/etal/2016a Piatkowski, Nico and Lee, Sangkyun and Morik, Katharina. Integer undirected graphical models for resource-constrained systems. In Neurocomputing, Vol. 173, No. 1, pages 9--23, Elsevier, 2016. Arrow Symbol
Lee/2015a Sangkyun Lee. Signature Selection for Grouped Features with A Case Study on Exon Microarrays. In Urszula Stańczyk and Lakhmi C. Jain (editors), Feature Selection for Data and Pattern Classification, pages 329--349, Springer, 2015.
Lee/etal/2015b Lee, Sangkyun and Brzyski, Damian and Bogdan, Malgorzata. Fast Saddle-Point Algorithm for Generalized Dantzig Selector and FDR Control with the Ordered $\ell_1$-Norm. In 19th International Conference on Artificial Intelligence and Statistics, 2015. Arrow Symbol
Lee/Poelitz/2015a Lee, Sangkyun and Pölitz, Christian. Kernel Matrix Completion for Learning Nearly Consensus Support Vector Machines. In Fred, Ana and De Marsico, Maria and Tabbone, Antoine (editors), Pattern Recognition Applications and Methods, Vol. 9443, pages 93--109, Springer, 2015.
Schramm/etal/2015a Schramm, Alexander and Köster, Johannes and Assenov, Yassen and Althoff, Kristina and Peifer, Martin and Mahlow, Ellen and Odersky, Andrea and Beisser, Daniela and Ernst, Corinna and Henssen, Anton G. and Stephan, Harald and Schröder, Christopher and Heukamp, Lukas and Engesser, Anne and Kahlert, Yvonne and Theissen, Jessica and Hero, Barbara and Roels, Frederik and Altmüller, Janine and Nürnberg, Peter and Astrahantseff, Kathy and Gloeckner, Christian and De Preter, Katleen and Plass, Christoph and Lee, Sangkyun and Lode, Holger N. and Henrich, Kai-Oliver and Gartlgruber, Moritz and Speleman, Frank and Schmezer, Peter and Westermann, Frank and Rahmann, Sven and Fischer, Matthias and Eggert, Angelika and Schulte, Johannes H.. Mutational dynamics between primary and relapse neuroblastomas. In Nature Genetics, Vol. 47, No. 8, pages 872--877, 2015. Arrow Symbol
Schwermer/Lee/2015a Schwermer, Melanie and Lee, Sangkyun and Köster, Johannes and van Maerken, Tom and Stephan, Harald and Eggert, Angelika and Morik, Katharina and Schulte, Johannes H. and Schramm, Alexander. Sensitivity to cdk1-inhibition is modulated by p53 status in preclinical models of embryonal tumors. In Oncotarget, 2015.
Lee/2014a Lee, Sangkyun. Sparse Inverse Covariance Estimation for Graph Representation of Feature Structure. In Holzinger, Andreas and Jurisica, Igor (editors), Interactive Knowledge Discovery and Data Mining in Biomedical Informatics, Vol. 8401, pages 227--240, Springer, 2014.
Lee/2014b Lee, Sangkyun. Characterization of Subgroup Patterns from Graphical Representation of Genomic Data. In \'Sl\c ezak, Dominik and Tan, Ah-Hwee and Peters, JamesF. and Schwabe, Lars (editors), Brain Informatics and Health, Vol. 8609, pages 516--527, Springer, 2014.
Lee/etal/2014a Sangkyun Lee and Jörg Rahnenführer and Michel Lang and Katleen de Preter and Pieter Mestdagh and Jan Koster and Rogier Versteeg and Raymond Stallings and Luigi Varesio and Shahab Asgharzadeh and Johannes Schulte and Kathrin Fielitz and Melanie Heilmann and Katharina Morik and Alexander Schramm. Robust Selection of Cancer Survival Signatures from High-Throughput Genomic Data Using Two-Fold Subsampling. In PLoS ONE, Vol. 9, pages e108818, 2014.
Lee/Poelitz/2014a Lee, Sangkyun and Pölitz, Christian. Kernel Completion for Learning Consensus Support Vector Machines in Bandwidth-Limited Sensor Networks. In International Conference on Pattern Recognition Applications and Methods, 2014. Arrow Symbol
Piatkowski/etal/2014a Piatkowski, Nico and Sangkyun, Lee and Morik,Katharina. The Integer Approximation of Undirected Graphical Models. In De Marsico, Maria and Tabbone, Antoine and Fred, Ana (editors), ICPRAM 2014 - Proceedings of the 3rd International Conference on Pattern Recognition Applications and Methods, ESEO, Angers, Loire Valley, France, 6-8 March, 2014, pages 296--304, SciTePress, 2014. Arrow Symbol
Lee/Schramm/2013a Lee, Sangkyun and Schramm, Alexander. Preprocessing of Affymetrix Exon Expression Arrays. No. 3, Technische Universität Dortmund, 2013.
Lee/Wright/2013a Lee, Sangkyun and Wright, Stephen J.. Stochastic Subgradient Estimation Training for Support Vector Machines. In Latorre Carmona, Pedro and S\'anchez, J. Salvador and Fred, Ana L.N. (editors), Mathematical Methodologies in Pattern Recognition and Machine Learning, Vol. 30, pages 67--82, Springer, 2013. Arrow Symbol
Piatkowski/etal/2013a Piatkowski, N. and Lee, S. and Morik, K.. Spatio-temporal random fields: compressible representation and distributed estimation. In Machine Learning, Vol. 93, No. 1, pages 115--139, Springer, 2013. Arrow Symbol
Lee/2012a Lee, Sangkyun. Improving Confidence of Dual Averaging Stochastic Online Learning via Aggregation. In German Conference on Artificial Intelligence (KI 2012), pages 229--232, 2012. Arrow Symbol
Lee/etal/2012a Lee, S. and Stolpe, M. and Morik, K.. Separable Approximate Optimization of Support Vector Machines for Distributed Sensing. In Flach, Peter A. and De Bie, Tijland and Cristianini, Nello (editors), Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2012, Bristol, UK, September 24-28, 2012. Proceedings, Part II, Vol. 7524, pages 387--402, Springer, 2012.
Lee/Wright/2012a Lee, Sangkyun and Wright, Stephen J.. ASSET: Approximate Stochastic Subgradient Estimation Training for Support Vector Machines. In International Conference on Pattern Recognition Applications and Methods (ICPRAM 2012), pages 223-228, 2012. Arrow Symbol
Lee/Wright/2012b Lee, Sangkyun and Wright, Stephen J.. Manifold Identification in Dual Averaging Methods for Regularized Stochastic Online Learning. In Journal of Machine Learning Research, Vol. 13, pages 1705--1744, 2012. Arrow Symbol
Piatkowski/etal/2012a Piatkowski, Nico and Lee, Sangkyun and Morik, Katharina. Spatio-Temporal Models For Sustainability. In Marwah, Manish and Ramakrishnan, Naren and Berges, Mario and Kolter, Zico (editors), Proceedings of the SustKDD Workshop within ACM KDD 2012, ACM, 2012. Arrow Symbol
Umaashankar/Lee/2012a Umaashankar, Venkatesh and Lee, Sangkyun. Optimization plugin for RapidMiner. No. 4, TU Dortmund University, 2012.
Lee/2011a Lee, Sangkyun. Optimization Methods for Regularized Convex Formulations in Machine Learning. University of Wisconsin--Madison, 2011.
Lee/Bockermann/2011a Lee, Sangkyun and Bockermann, Christian. Scalable stochastic gradient descent with improved confidence. In Big Learning -- Algorithms, Systems, and Tools for Learning at Scale, 2011. Arrow Symbol
Lee/etal/2011a Lee, Sangkyun and Schowe, Benjamin and Sivakumar, Viswanath and Morik, Katharina. Feature Selection for High-Dimensional Data with RapidMiner. No. 1, TU Dortmund University, 2011.
Lee/Wright/2011a Lee, Sangkyun and Wright, Stephen J.. Manifold Identification of Dual Averaging Methods for Regularized Stochastic Online Learning. In the 28th International Conference on Machine Learning, 2011. Arrow Symbol
Lee/Wright/2011b Lee, Sangkyun and Wright, Stephen J.. Manifold Identification in Dual Averaging Methods for Regularized Stochastic Online Learning. University of Wisconsin-Madison, 2011. Arrow Symbol
Lee/Wright/2009a Lee, Sangkyun and Wright, Stephen J.. Decomposition Algorithms for Training Large-scale Semiparametric Support Vector Machines. In Buntine, Wray and Grobelnik, Marko and Mladenic, Dunja and Shawe-Taylor, John (editors), Machine Learning and Knowledge Discovery in Databases, Vol. 5782, pages 1-14, Springer, 2009. Arrow Symbol
Lee/Wright/2009b Lee, Sangkyun and Wright, Stephen J.. Signal Processing Algorithms on Graphical Processing Units. In INFORMS Annual Meeting, 2009.
Lee/Wright/2009c Lee, Sangkyun and Wright, Stephen J.. Decomposition and Stochastic Subgradient Algorithms for Support Vector Machines. In 20th International Symposium on Mathematical Programming, 2009. Arrow Symbol
Lee/Wright/2008a Lee, Sangkyun and Wright, Stephen J.. Implementing Algorithms for Signal and Image Reconstruction on Graphical Processing Units. University of Wisconsin-Madison, 2008. Arrow Symbol
Lee/etal/2006a Lee, Sangkyun and Lee, S.-J. and Zhang, B.-T.. Combining Information-based Supervised and Unsupervised Feature Selection. In Isabelle Guyon, Steve Gunn, Masoud Nikravesh, Lofti A. Zadeh (editors), Feature Extraction: Foundations and Applications, Springer, 2006. Arrow Symbol
Lee/2005a Lee, Sangkyun. Integrating Different Species Pairwise Information Using Multiple Relational Embedding Techniques. Seoul National University, 2005.

Software

Supervised Theses

Membership

Conference program committee member of:

  • NIPS, KDD, IJCAI, ECML/PKDD, ACML, ECAI, DATA, ECCB, IEEE ICDM, IEEE ICDE

Journal reviewer of:

  • Machine Learning
  • Artificial Intelligence
  • IEEE Trans. Neural Networks and Learning Systems
  • SIAM Journal on Scientific Computing
  • Optimization Methods and Software
  • Data Mining and Knowledge Discovery
  • Knowledge and Information Systems

Grant proposal referee of:

  • DFG: German Science Foundation
  • NCN: National Science Centre, Poland

Visiting Scholar of:

Awards

  • Best student paper award, Journal Track (Machine Learning) of ECML/PKDD 2013
  • Samsung Scholarship, Samsung Foundation of Culture, 2005-2010