Jaewoo Lee

My Profile

I am an associate professor in School of Computing at University of Georgia. Before joining UGA, I was a postdoctoral research associate working in Prof. Daniel Kifer's machine learning lab at PennState university. I received my Ph.D. in computer science in 2014 from Purdue university, where I studied privacy-preserving data analysis techniques under the supervision of Prof. Chris Clifton. Before joining Purdue, I was a member of database group at Yonsei university where I obtained my master and bachelor degrees in Computer Science. During my master study, I did research on developing efficient stream mining algorithms for high-dimensional data streams under the supervision of Prof. Won Suk Lee.

Teaching

• CSCI 3360 Data Science I
• CSCI 8960 Privacy-Preserving Data Analysis
• CSCI 4260/6260 Data Security and Privacy
• CSCI 2610 Discrete Mathematics for Computer Science
• PPML Summer School (resource)

Research

My primary research interests lie in the field of machine learning, numerical optimization, and their interaction with statistical data privacy (such as differential privacy). I work on developing new statistical models and algorithms for performing various machine learning (including deep learning) tasks on sensitive data. The research topics of my interests are listed below, but not limited to:

• Machine learning
• Numerical optimization
• Statistical data privacy
• Security analytics

Publication

• Soham Sajekar, Sanika Katekar, and Jaewoo Lee
  Diffusion Augmented Flows: Combining Normalizing Flows and Diffusion Models for Accurate Latent Space Mapping
  FICC 2024
• Juyeon Seo, Jaewoo Lee, Juhyun Lee, and Hyunsuk Ko
  Deep compression network for enhancing numerical reconstruction quality of full-complex holograms
  Optics Express, 2023
• Yongrok Kim, Won Shin, Jaewoo Lee, Kwan-Jung Oh, and Hyunsuk Ko
  Performance analysis of versatile video coding for encoding phase-only hologram videos
  Optics Express 2023
• Jaewoo Lee
  MBAG: A Scalable Mini-Block Adaptive Gradient Method for Deep Neural Networks
  IEEE BigData 2022
• Jaewoo Lee, Minjung Kim, Yonghyun Jeong, and Youngmin Ro
  Differentially Private Normalizing Flows for Synthetic Tabular Data Generation
  AAAI 2022
• Shivani Arbat, Vinod Jayakumar, Jaewoo Lee, Wei Wang, and In Kee Kim
  Wasserstein Adversarial Transformer for Cloud Workload Prediction
  IAAI 2022
• Seung Woo Kwak, Jeongyoun Ahn, Jaewoo Lee, and Cheolwoo Park
  Differentially Private Goodness-of-Fit Tests for Continuous Variables
  Econometrics and Statistics 2021
• Sen He, Tianyi Liu, Palden Lama, Jaewoo Lee, In Kee Kim, and Wei Wang.
  Performance Testing for Cloud Computing with Dependent Data Bootstrapping
  IEEE/ACM ASE 2021
• Amanda Giordano, Lindsay Lundeen, Kelly Wester, Jaewoo Lee, Samuel Vickers, Michael Schmit, and In Kee Kim
  Nonsuicidal self-injury on Instagram: Examining hashtag trends
  International Journal for the Advancement of Counselling, 2021
• Jaewoo Lee and Daniel Kifer
  Scaling up Differentially Private Deep Learning with Fast Per-Example Gradient Clipping
  PETS 2021
• Chen Chen and Jaewoo Lee
  Stochastic Adaptive Line Search for Differentially Private Optimization
  IEEE BIG DATA 2020 (Regular paper)
• Jaewoo Lee and Daniel Kifer
  Differentially Private Deep Learning with Direct Feedback Alignment
  In preparation (Arxiv 2020)
• Daniele Ucci, Roberto Perdisci, Jaewoo Lee, Mustaque Ahamad
  Building a Collaborative Phone Blacklisting System with Local Differential Privacy
  ACSAC 2020
• Chen Chen, Jaewoo Lee
  Renyi Differentially Private ADMM for Non-smooth Regularized Optimization
  IEEE CODASPY 2020
• Vinodh K. Jayakumar, Jaewoo Lee, In Kee Kim, Wei Wang
  A Self-Optimized Generic Workload Prediction Framework for Cloud Computing
  IEEE IPDPS 2020
• Lei Xian, Samuel Dakota Vickerss, Amanda L. Giordano, Jaewoo Lee, In Kee Kim, Lakshmish Ramaswamy
  #selfharm on Instagram: Quantitative Analysis and Classification of Non-Suicidal Self-Injury
  IEEE CogMI 2019
• Chen Chen, Jaewoo Lee, and Daniel Kifer
  Renyi Differentially Private ERM for Smooth Objectives
  AISTATS 2019 (Oral presentation)
• Yue Wang, Daniel Kifer, and Jaewoo Lee
  Differentially Private Confidence Intervals for Empirical Risk Minimization
  Journal of Privacy and Confidentiality, 2019
• Yue Wang, Daniel Kifer, Jaewoo Lee, and Visesh Karwa
  Statistical Approximating Distributions Under Differential Privacy
  Journal of Privacy and Confidentiality, 2018
• Jaewoo Lee and Daniel Kifer
  Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
  In Proceedings of the 24th ACM SIGKDD international conference on Knowledge discovery and data mining (2018)
• Jaewoo Lee
  Differentially Private Variance Reduced Stochastic Gradient
  International Conference on new Trends in Computing Sciences, 2017
• Jaewoo Lee and Daniel Kifer
  Postprocessing for Iterative Differentially Private Algorithms
  ICML Workshop on Theory and Practice of Differential Privacy, 2016
• Yue Wang, Jaewoo Lee and Daniel Kifer
  Differentially Private Hypothesis Testing, Revisited
  ArXiv. Nov. 2015
• Jaewoo Lee, Yue Wang, and Daniel Kifer
  Maximum Likelihood Postprocessing for Differential Privacy under Consistency Constraints
  In Proceedings of the 21th ACM SIGKDD international conference on Knowledge discovery and data mining (2015)
• Jaewoo Lee and Daniel Kifer
  Top-k Frequent Itemsets via Differentially Private FP-trees^†
  In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (2014)
• Jaewoo Lee and Chris Clifton
  Differential Identifiability
  In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining (2012)
• Jaewoo Lee and Chris Clifton
  How much is enough?: Choosing epsilon for Differential Privacy
  In Proceedings of the 14th Information Security international conference (2011)
• Hazem Elmeleegy, Ahmed Elmagarmid and Jaewoo Lee
  Leveraging Query Logs for Schema Mapping Generation in U-MAP
  In Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data (2011)
• Hazem Elmeleegy,Jaewoo Lee, El Kindi Rezig, Mourad Ouzzani, Ahmed Elmagarmid
  U-MAP: A System for Usage-based Schema Matching and Mapping (demo)
  In Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data (2011)
• Jae Woo Lee, Nam Hun Park, Won Suk Lee
  Efficiently Tracing Clusters over High-dimensional On-line Data Streams
  In Journal of Data Knowledge Engineering (2009)
• Jae Woo Lee and Won Suk Lee
  A Coarse-grain Grid-based Subspace Clustering Method for Online Multi-dimensional Data Streams
  In Proceedings of the 17th ACM Conference on Information and Knowledge Management (2008)
• Rajesh Kalyanam, Lan Zhao, Carol X. Song, Yuet Ling Wong,Jaewoo Lee, Nelson B. Villoria
  iData: a community geospatial data sharing environment to support data-driven science
  In Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery (2013)

†Unfortunately, the algorithm proposed in this paper has a technical problem and the privacy is not guaranteed. For details, see here