Link Search Menu Expand Document

For the complete lists of papers, see Preprints, Conference Papers, and Journal Papers. Shown below is the list of selected papers.

Current Research Topics

Overarching theme: We study theoretical aspects of machine learning to develop better ML algorithms and systems.

Theory

  • A Better Way to Decay: Proximal Gradient Training Algorithms for Neural Nets
    L. Yang, J. Zhang, J. Shenouda, D. Papailiopoulos, K. Lee, and R. Nowak
    Arxiv, 2022
    NeurIPS OPT Workshop, 2022
  • Score-based generative modeling secretly minimizes the Wasserstein distance
    D. Kwon, Y. Fan, and K. Lee
    NeurIPS 2022
  • Permutation-Based SGD: Is Random Optimal?
    S. Rajput, K. Lee, and D. Papailiopoulos
    ICLR 2022
  • Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
    C. Jo, and K. Lee
    ICML 2021
  • Community Recovery in Hypergraphs
    K. Ahn, K. Lee, and C. Suh
    IEEE Transactions on Information Theory 2019
  • Binary Rating Estimation with Graph Side Information
    K. Ahn, K. Lee, H. Cha, and C. Suh
    NeurIPS 2018
  • Hypergraph Spectral Clustering in the Weighted Stochastic Block Model
    K. Ahn, K. Lee, and C. Suh
    IEEE Journal of Selected Topics in Signal Processing 2018

Transformers and large pretrained models (GPT, CLIP, diffusion models, …)

  • Optimizing DDPM Sampling with Shortcut Fine-Tuning
    Ying Fan, Kangwook Lee
    Arxiv 2023
  • Looped Transformers as Programmable Computers
    Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
    Arxiv, 2023
  • Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
    T. Dinh, J. Sohn, S. Rajput, T. Ossowski, Y. Ming, J. Hu, D. Papailiopoulos and K. Lee
    Findings of EMNLP 2022
  • LIFT: Language-Interfaced FineTuning for Non-Language Machine Learning Tasks
    T. Dinh*, Y. Zeng*, R. Zhang, Z. Lin, M. Gira, S. Rajput, J. Sohn, D. Papailiopoulos and K. Lee
    NeurIPS 2022

Trustworthy ML (fairness, robustness, privacy, …)

  • Improving Fair Training under Correlation Shifts
    Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh
    Arxiv 2023
  • Outlier-Robust Group Inference via Gradient Space Clustering
    Y. Zeng, K. Greenewald, K. Lee, J. Solomon, and M. Yurochkin
    Arxiv 2022
  • Equal Improvability: A New Fairness Notion Considering the Long-Term Impact
    O. Guldogan, Y. Zeng, J. Sohn, R. Pedarsani, and K. Lee
    ICLR 2023
  • Improving Fairness via Federated Learning
    Y. Zeng, H. Chen, and K. Lee
    MLSys-CrossFL 2022, AAAI 2022 Workshop on Federated Learning
  • GenLabel: Mixup Relabeling using Generative Models
    J. Sohn, L. Shang, H. Chen, J. Moon, D. Papailiopoulos, and K. Lee
    ICML 2022
  • Breaking Fair Binary Classification with Optimal Flipping Attacks
    C. Jo, J. Sohn, and K. Lee
    ISIT 2022
  • Sample Selection for Fair and Robust Training
    Y. Roh, K. Lee, S. Whang, and C. Suh
    NeurIPS 2021
  • Gradient Inversion with Generative Image Prior
    J. Kim, J. Jeon, K. Lee, S. Oh, and J. Ok
    NeurIPS 2021
  • FairBatch: Batch Selection for Model Fairness
    Y. Roh, K. Lee, S. Whang, and C. Suh
    ICLR 2021
  • FR-Train: A mutual information-based approach to fair and robust training
    Y. Roh, K. Lee, S. Whang, and C. Suh
    ICML 2020
  • Synthesizing Differentially Private Datasets using Random Mixing
    K. Lee, H. Kim, K. Lee, C. Suh, and K. Ramchandran
    IEEE ISIT 2019

Distributed ML (Coded computation, distributed learning, federated learning, …)

  • Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification
    S. Agarwal, H. Wang, K. Lee, S. Venkataraman, and D. Papailiopoulos
    MLSys 2021
  • Coded-InvNet for Resilient Prediction Serving Systems
    T. Dinh, and K. Lee
    ICML 2021 (long oral)
  • Attack of the Tails: Yes, You Really Can Backdoor Federated Learning
    H. Wang, K. Sreenivasan, S. Rajput, H. Vishwakarma, S. Agarwal, J. Sohn, K. Lee, and D. Papailiopoulos
    NeurIPS 2020
  • Speeding Up Distributed Machine Learning Using Codes
    K. Lee, M. Lam, R. Pedarsani, D. Papailiopoulos, and K. Ramchandran
    IEEE Transactions on Information Theory January 2018 (The Joint Communications Society/Information Theory Society Paper Award, 2020)
  • High-Dimensional Coded Matrix Multiplication
    K. Lee, C. Suh, and K. Ramchandran
    IEEE ISIT 2017

Efficient ML

  • Active Learning is a Strong Baseline for Data Subset Selection
    D. Park, D. Papailiopoulos, K. Lee
    NeurIPS HITY Workshop 2022
  • Rare Gems: Finding Lottery Tickets at Initialization
    K. Sreenivasan, J. Sohn, L. Yang, M. Grinde, A. Nagle, H. Wang, K. Lee, D. Papailiopoulos
    NeurIPS 2022

Past Research Topics

GANs

  • Improved Input Reprogramming for GAN Conditioning
    T. Dinh, D. Seo, Z. Du, L. Shang, and K. Lee
    ICML Workshop on Updatable Machine Learning (UpML 2022)
  • Reprogramming GANs via Input Noise Design
    K. Lee, C. Suh, and K. Ramchandran
    ECML PKDD 2020
  • Crash to Not Crash: Learn to Identify Dangerous Vehicles using a Simulator
    H. Kim, K. Lee, G. Hwang, and C. Suh
    AAAI 2019 (oral)
  • Simulated+Unsupervised Learning With Adaptive Data Generation and Bidirectional Mappings
    K. Lee, H. Kim, and C. Suh
    ICLR 2018

Codes for efficient sparse signal recovery

  • SAFFRON: Sparse-Graph Code Framework for Group Testing
    K. Lee, R. Pedarsani, and K. Ramchandran
    IEEE Transactions on Signal Processing 2019
  • PhaseCode: Fast and Efficient Compressive Phase Retrieval based on Sparse-Graph-Codes
    R. Pedarsani, D. Yin, K. Lee, and K. Ramchandran
    IEEE Transactions on Information Theory 2017

MDS queue & Redundant requests

  • The MDS Queue: Analysing the Latency Performance of Erasure Codes
    K. Lee, N. Shah, L. Huang, and K. Ramchandran
    IEEE Transactions on Information Theory 2017
  • On Scheduling Redundant Requests With Cancellation Overheads
    K. Lee, R. Pedarsani, and K. Ramchandran
    IEEE/ACM Transactions on Networking 2017
  • When Do Redundant Requests Reduce Latency?
    N. Shah, K. Lee, and K. Ramchandran
    IEEE Transactions on Communications 2016