avatar

Jaewoo Lee

Associate Professor
University of Georgia
jaewoo (dot) lee (at) uga.edu


Publications

  1. Low-Rank Curvature for Zeroth-Order Optimization in LLM Fine-tuning
    Hyunseok Seung, Jaewoo Lee, and Hyunsuk Ko
    AAAI Conference on Artificial Intelligence, 2026   AAAI
    PDF Code   Acceptance rate 17.6%
  2. Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning
    Qitao Tan, Jun Liu, Zheng Zhan, Caiwen Ding, Yanzhi Wang, Xiaolong Ma, Jaewoo Lee, Jin Lu, and Geng Yuan
    Annual Conference on Neural Information Processing Systems, 2025   NeurIPS
    PDF
  3. MAC: An Efficient Gradient Preconditioning using Mean Activation Approximated Curvature
    Hyunseok Seung, Jaewoo Lee, and Hyunsuk Ko
    IEEE International Conference on Data Mining, 2025   ICDM
    PDF
  4. NysAct: A Scalable Preconditioned Gradient Descent Using Nyström Approximation
    Hyunseok Seung, Jaewoo Lee, and Hyunsuk Ko
    IEEE International Conference on BigData, 2024   BigData
    PDF
  5. An Adaptive Method Stabilizing Activations for Enhanced Generalization
    Hyunseok Seung, Jaewoo Lee, and Hyunsuk Ko
    IEEE ICDM Workshop on Optimization Based Techniques for Emerging Data Mining Problems, 2024   ICDMW
    PDF
  6. PPSA: Polynomial Private Stream Aggregation for Time-Series Data Analysis
    Antonia Januszewicz, Daniela Medrano Gutierrez, Nirajan Koirala, Jiachen Zhao, Jonathan Takeshita, Jaewoo Lee, Taeho Jung
    EAI International Conference on Security and Privacy in Communication Networks, 2024   SecureComm
    PDF
  7. Diffusion Augmented Flows: Combining Normalizing Flows and Diffusion Models for Accurate Latent Space Mapping
    Soham Sajekar, Sanika Katekar, and Jaewoo Lee
    Future of Information and Communication Conference, 2024   FICC
    PDF
  8. Deep compression network for enhancing numerical reconstruction quality of full-complex holograms
    Juyeon Seo, Jaewoo Lee, Juhyun Lee, and Hyunsuk Ko
    Opt. Express, 31(15):24573–24597, Jul 2023   Opt. Express
    PDF   IF 3.2
  9. Performance analysis of versatile video coding for encoding phase-only hologram videos
    Yongrok Kim, Won Shin, Jaewoo Lee, Kwan-Jung Oh, and Hyunsuk Ko
    Opt. Express, 31(23):38854–38877, Nov 2023   Opt. Express
    PDF   IF 3.2
  10. Federated Learning and Analysis for Collaborative Research in Healthcare at a National and International Scale
    Michael Chassé, Louis Mullie, Philippe Després, Vincent Ferretti, Jessica Kissinger, Jaewoo Lee, Wenzhan Song, Peter Zinterhof, Christian Wachinger, and Bjoern Eskofier
    Online article 2023  
    PDF
  11. MBAG: A Scalable Mini-Block Adaptive Gradient Method for Deep Neural Networks.
    Jaewoo Lee
    IEEE International Conference on Big Data, 2022   BigData
    PDF
  12. Differentially Private Normalizing Flows for Synthetic Tabular Data Generation
    Jaewoo Lee, Minjung Kim, Yonghyun Jeong, and Youngmin Ro
    AAAI Conference on Artificial Intelligence, 2022   AAAI
    PDF
  13. Wasserstein Adversarial Transformer for Cloud Workload Prediction
    Shivani Arbat, Vinod Jayakumar, Jaewoo Lee, Wei Wang, and In Kee Kim
    Annual Conference on Innovative Applications of Artificial Intelligence (IAAI), 2022   IAAI
    PDF
  14. Differentially Private Goodness-of-Fit Tests for Continuous Variables
    Seung Woo Kwak, Jeongyoun Ahn, Jaewoo Lee, and Cheolwoo Park
    Econometrics and Statistics, Volume 31, July 2024, Pages 81-99   ECOSTA
    PDF
  15. Performance Testing for Cloud Computing with Dependent Data Bootstrapping
    Sen He, Tianyi Liu, Palden Lama, Jaewoo Lee, In Kee Kim, and Wei Wang
    IEEE/ACM International Conference on Automated Software Engineering, 2021   ASE
    PDF
  16. Nonsuicidal self-injury on Instagram: Examining hashtag trends
    Amanda Giordano, Lindsay Lundeen, Kelly Wester, Jaewoo Lee, Samuel Vickers, Michael Schmit, and In Kee Kim
    International Journal for the Advancement of Counselling, 2021  
    PDF
  17. Scaling up Differentially Private Deep Learning with Fast Per-example Gradient Clipping
    Jaewoo Lee and Daniel Kifer
    Privacy Enhancing Technologies, 2021(1)   PETS
    PDF
  18. Stochastic Adaptive Line Search for Differentially Private Optimization
    Chen Chen and Jaewoo Lee
    IEEE International Conference on Big Data, 2020   BigData
    PDF
  19. Towards a Practical Differentially Private Collaborative Phone Blacklisting System
    Daniele Ucci, Roberto Perdisci, Jaewoo Lee, and Mustaque Ahamad
    Annual Computer Security Applications Conference, 2020   ACSAC
    PDF
  20. Renyi Differentially Private ADMM for Non-Smooth Regularized Optimization
    Chen Chen and Jaewoo Lee
    ACM Conference on Data and Application Security and Privacy, 2020   CODASPY
    PDF
  21. A Self-Optimized Generic Workload Prediction Framework for Cloud Computing
    Vinodh K. Jayakumar, Jaewoo Lee, In Kee Kim, and Wei Wang
    IEEE International Parallel and Distributed Processing Symposium, 2020   IPDPS
    PDF
  22. Differentially private deep learning with direct feedback alignment
    Jaewoo Lee and Daniel Kifer
    ArXiv, 2019   ArXiv
    PDF
  23. Selfharm on Instagram: Quantitative Analysis and Classification of Non-Suicidal Self-Injury
    Lei Xian, Samuel D. Vickers, Amanda L. Giordano, Jaewoo Lee, In Kee Kim, and Lakshmish Ramaswamy
    IEEE International Conference on Cognitive Machine Intelligence, 2019   CogMI
    PDF
  24. Renyi Differentially Private ERM for Smooth Objectives
    Chen Chen, Jaewoo Lee, and Daniel Kifer
    International Conference on Artificial Intelligence and Statistics, 2019   AISTATS
    PDF
  25. Differentially Private Confidence Intervals for Empirical Risk Minimization
    Yue Wang, Daniel Kifer, and Jaewoo Lee
    Journal of Privacy and Confidentiality, 9(1), 2019   JPC
    PDF
  26. Statistical Approximating Distributions Under Differential Privacy
    Yue Wang, Daniel Kifer, Jaewoo Lee, and Vishesh Karwa
    Journal of Privacy and Confidentiality, 8(1), 2018   JPC
    PDF
  27. Concentrated Differentially Private Gradient Descent with Adaptive per-Iteration Privacy Budget
    Jaewoo Lee and Daniel Kifer
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2018   KDD
    PDF   Acceptance rate 10.8%
  28. Differentially Private Variance Reduced Gradient
    Jaewoo Lee
    International Conference on New Trends in Computing Sciences, 2017   ICTCS
    PDF
  29. Postprocessing for Iterative Differentially Private Algorithms
    Jaewoo Lee and Daniel Kifer
    ICML 2016 Workshop on Theory and Practice of Differential Privacy   TPDP
      poster
  30. Differentially Private Hypothesis Testing, Revisited
    Yue Wang, Jaewoo Lee, and Daniel Kifer
    ArXiv, 2016   ArXiv
    PDF
  31. Maximum Likelihood Postprocessing for Differential Privacy under Consistency Constraints
    Jaewoo Lee, Yue Wang, and Daniel Kifer
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2015   KDD
    PDF   Acceptance rate 19.4%
  32. Top-k Frequent Itemsets via Differentially Private FP-trees
    Jaewoo Lee and Chris Clifton
    ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014   KDD
    PDF   Acceptance rate 14.6%
  33. iData: A Community Geospatial Data Sharing Environment to Support Data-driven Science
    Rajesh Kalyanam, Lan Zhao, Carol X. Song, Yuet Ling Wong, Jaewoo Lee, and Nelson B. Villoria
    Conference on Extreme Science and Engineering Discovery Environment Gateway to Discovery, 2013   XSEDE
  34. Differential identifiability
    Jaewoo Lee and Chris Clifton
    ACM SIGKDD international conference on Knowledge discovery and data mining, 2012   KDD
    PDF   Acceptance rate 17.6%
  35. How much is enough? Choosing ϵ for Differential Privacy
    Jaewoo Lee and Chris Clifton
    Information Security, volume 7001 of LNCS, pages 325–340   ISC
    PDF
  36. Leveraging Query Logs for Schema Mapping Generation in U-MAP
    Hazem Elmeleegy, Ahmed Elmagarmid, and Jaewoo Lee
    ACM SIGMOD International Conference on Management of Data, 2011   SIGMOD
    PDF
  37. U-MAP: A System for Usage-based Schema Matching and Mapping
    Hazem Elmeleegy, Jaewoo Lee, El Kindi Rezig, Mourad Ouzzani, and Ahmed Elmagarmid
    ACM SIGMOD International Conference on Management of Data, 2011   SIGMOD
      demo paper
  38. Efficiently Tracing Clusters over High-dimensional On-line Data Streams
    Jae Woo Lee, Nam Hun Park, and Won Suk Lee
    Data Knowledge & Engineering (DKE), 68(3):362–379, March 2009   DKE
    PDF
  39. A Coarse-grain Grid-based Subspace Clustering Method for Online Multi-dimensional Data Streams
    Jae Woo Lee and Won Suk Lee
    ACM Conference on Information and Knowledge Management, 2008   CIKM
    PDF