Fair Dimensionality Reduction

Junghyun Lee
Oct 27, 2020 project

Project #1. Fair PCA

Fair Principal Component Analysis: Statistical and Algorithmic Viewpoints

  • Work in progress for journal.
  • Joint work with Hanseul Cho, Se-Young Yun, & Chulhee Yun (KAIST AI), and Gwangsu Kim & Seungyong Hwang (JBNU Statistics).

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

  • Accepted to NeurIPS 2023.
  • Joint work with Hanseul Cho, Se-Young Yun, and Chulhee Yun (KAIST AI).

Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold

  • Accepted to AAAI 2022.
  • Joint work with Gwangsu Kim, Chang D. Yoo (KAIST EE), Matt Olfat (UC Berkeley IEOR), and Mark Hasegawa-Johnson (UIUC ECE).
Fairness PCA Statistics Optimization
Junghyun Lee
Junghyun Lee
PhD Student

PhD student at GSAI, KAIST, jointly advised by Profs. Se-Young Yun and Chulhee Yun. Research focuses on interactive machine learning, particularly at the intersection of RLHF and preference learning, and statistical analyses of large networks, with an emphasis on community detection. Broadly interested in mathematical and theoretical AI and related problems in mathematics.

Posts

One paper accepted to NeurIPS 2023!
One paper (Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint) is accepted to NeurIPS 2023! This is joint work with my advisors Se-Young Yun and Chulhee Yun (KAIST AI), and my wonderful collaborator Hanseul Cho (KAIST AI).
Junghyun Lee
Sep 22, 2023 1 min read
Project
One paper accepted to AAAI 2022!
One paper (Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold) is accepted to AAAI 2022! This is joint work with Gwangsu Kim and Chang D. Yoo (KAIST EE), Matt Olfat (UC Berkeley IEOR & Citadel), and Mark Hasegawa-Johnson (UIUC EE).
Junghyun Lee
Dec 1, 2021 1 min read
Project
One paper accepted to JKAIA 2021 + selected as one of the best papers!
One paper (MMD-based Fair PCA via Manifold Optimization) is accepted to JKAIA 2021! This is joint work with Gwangsu Kim and Chang D. Yoo (KAIST EE), Matt Olfat (UC Berkeley IEOR & Citadel), and Mark Hasegawa-Johnson (UIUC EE).
Junghyun Lee
Nov 1, 2021 1 min read
Project

Publications

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
Proposes a framework for performing fair PCA in memory limited, streaming setting. Sample complexity results and empirical discussions show the superiority of our approach compared to the existing approaches.
Junghyun Lee, Hanseul Cho, Se-Young Yun, Chulhee Yun
PDF Cite Code Project Poster Slides
Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint
Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold
Proposes a new MMD-based definition of fairness for PCA, then formulate fair PCA as an optimization over the Stiefel manifold. Various theoretical and empirical discussions show the superiority of our approach compared to the existing approach (Olfat & Aswani, AAAI'19).
Junghyun Lee, Gwangsu Kim, Matt Olfat, Mark Hasegawa-Johnson, Chang D. Yoo
PDF Cite Code Project Poster Slides
Fast and Efficient MMD-based Fair PCA via Optimization over Stiefel Manifold