Lee Lab @ UW Madison

News

(Dec. 2022) Dr. Sohn will join Yonsei University as an assistant professor! Congratulations!
(July. 2022) Prof. Lee received UW Madison ECE Grainger Faculty Scholarship Award.
(Mar. 2022) Prof. Lee received 2022 KSEA Young Investigator Grants.

(2023) Score-based generative modeling secretly minimizes the Wasserstein distance (Information Theory and Data Science Workshop, UW Madison SILO)
(2022, 2023) On a bilevel optimization approach to fair classification (USC EE, UCSB CCDC, IOS’22, US-Mexico Workshop on Optimization and its Applications’23)
(2021, 2022) Improving Fairness via Federated Learning (UC Berkeley BLISS, KAIST AI International Symposium)
(2021) Information Theory and Coding for Trustworthy and Scalable Machine Learning (Seoul National University, POSTECH AI)

Looped Transformers as Programmable Computers
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
Arxiv, 2023
Active Learning is a Strong Baseline for Data Subset Selection
D. Park, D. Papailiopoulos, K. Lee
NeurIPS HITY Workshop, 2022
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
Outlier-Robust Group Inference via Gradient Space Clustering
Y. Zeng, K. Greenewald, K. Lee, J. Solomon, and M. Yurochkin
Arxiv, 2022

[ICLR’23] Equal Improvability: A New Fairness Notion Considering the Long-Term Impact. (Github)
[Findings of EMNLP’22] Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment. (Github) (A short summary)
[NeurIPS’22] Score-based generative modeling secretly minimizes the Wasserstein distance. (Github) (A short summary)
[NeurIPS’22] LIFT: Language-Interfaced FineTuning for Non-Language Machine Learning Tasks. (Github) (A short summary)
[NeurIPS’22] Rare Gems: Finding Lottery Tickets at Initialization
[ICML’22] GenLabel: Mixup Relabeling using Generative Models
[ICLR’22] Permutation-Based SGD: Is Random Optimal?
[ISIT’22] Breaking Fair Binary Classification with Optimal Flipping Attacks
[NeurIPS’21] Sample Selection for Fair and Robust Training
[NeurIPS’21] Gradient Inversion with Generative Image Prior
[ICML’21] Coded-InvNet for Resilient Prediction Serving Systems long oral
[ICML’21] Discrete-Valued Latent Preference Matrix Estimation with Graph Side Information
[MLSys’21] Accordion: Adaptive Gradient Communication via Critical Learning Regime Identification.
[ICLR’21] FairBatch: Batch Selection for Model Fairness