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
Probability Theory
Heavy-tail behaviour of SGD - Part 1
Event Weekly OSI Lab Seminar Short summary In this seminar, I will talk about a recent line of works that propose to analyze SGD under heavy-tail noise assumptions. Abstract One of the popular ways of analyzing the behavior of SGD and SGDm(SGD with momentum) is by considering it as a discretization of Langevin-type SDE.
Aug 14, 2020
Probability-Flow ODE in Infinite-Dimensional Function Spaces
Recent advances in infinite-dimensional diffusion models have demonstrated their effectiveness and scalability in function generation …
Kunwoo Na
,
Junghyun Lee
,
Se-Young Yun
,
Sungbin Lim
PDF
Cite
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
We present a unified likelihood ratio-based confidence sequence (CS) for any (self-concordant) generalized linear model (GLM) that is …
Junghyun Lee
,
Se-Young Yun
,
Kwang-Sung Jun
PDF
Cite
Code
Project
Poster
Slides
Improved Regret Bounds of (Multinomial) Logistic Bandits via Regret-to-Confidence-Set Conversion
Logistic bandit is a ubiquitous framework of modeling users’ choices, e.g., click vs. no click for advertisement recommender …
Junghyun Lee
,
Se-Young Yun
,
Kwang-Sung Jun
PDF
Cite
Code
Project
Poster
Slides
Deep Learning Theory - Optimization
specific topics tbd
Junghyun Lee
Statistical Learning in Structured Markov Chains and MDPs
Project #1. Clustered State Space Nearly Optimal Latent State Decoding in Block MDPs Accepted to AISTATS 2023 Joint work with Se-Young Yun (KAIST AI) and Yassir Jedra, Alexandre Proutière (KTH EECS).
Junghyun Lee
Statistical Problems Related to (LLM) Alignment and Preference Learning
(tbd)
Junghyun Lee
«
Cite
×