Junghyun Lee
Junghyun Lee
Home
Experiences
Publications
Projects
Posts
Seminars
Organizer
Korean AI Theory Community Workshop
SNU-KAIST ML/AI Theory Workshop
Machine/Deep Learning Theory + Physics Seminar
Contact
Light
Dark
Automatic
Statistics
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
Nearly Optimal Latent State Decoding in Block MDPs
First theoretical analysis of model estimation and reward-free RL of block MDP, without resorting to function approximation frameworks. Lower bounds and algorithms with near-optimal upper bound are provided.
Yassir Jedra
,
Junghyun Lee
,
Alexandre Proutière
,
Se-Young Yun
PDF
Cite
Code
Project
Poster
Slides
Preliminary Empirical Analyses of Clustering in Block MDPs
We empirically validate the clustering algorithm proposed in (Jedra et al., 2022).
Junghyun Lee
,
Se-Young Yun
PDF
Cite
Project
Slides
A Statistical Analysis of Stochastic Gradient Noises for GNNs
Inspired from (Wang et al., ICLR'22), we provide a preliminary statistical analysis of stochastic gradient noises (SGNs) of GIN and GCN in Cora node classification task.
Junghyun Lee
,
Minchan Jeong
,
Namgyu Ho
,
Se-Young Yun
PDF
Cite
Project
Slides
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
Disagreement-based Active Learning
Developed least disagree metric (LDM), a new disagreement-based uncertainty measure, and an LDM-based active learning algorithm with state-of-the-art performance guarantee.
Junghyun Lee
Fair Dimensionality Reduction
Part of fair representation learning. Develop a theory of fairness in dimensionality reduction: new definition, new (efficient) algorithm, new theoretical results. Currently focused on PCA.
Junghyun Lee
Sample Complexity of Learning in Structured Markov Chains and MDPs
(tbd)
Junghyun Lee
Theoretical Analyses of Reinforcement Learning with Human Feedback (RLHF) and Related Problems
(tbd)
Junghyun Lee
«
Cite
×