Yunbum Kook
Office: 2210 KACB
Email: yb.{last name} at gatech dot edu

I am a fifth-year PhD student in CS at Georgia Tech, advised by Santosh Vempala. I received my B.S. in Mathematical Sciences from KAIST. I am interested in high-dimensional sampling and, more broadly, the foundations of machine learning and data science. In Spring and Summer 2025, I was a student researcher at Google Research, supervised by Matthew Fahrbach.

Scholar   CV  

Publications

A unified complexity bound for logconcave sampling
with Santosh S. Vempala
arXiv  

Covariance estimation using Markov chain Monte Carlo
with Matthew S. Zhang
arXiv   ICML 2026

The localization method for high-dimensional inequalities
with Santosh S. Vempala
arXiv   [FOCS 2025 workshop]   [Video 1, 2] 

Zeroth-order logconcave sampling
with Santosh S. Vempala
arXiv   Slide  

Faster logconcave sampling from a cold start in high dimension
with Santosh S. Vempala
arXiv   FOCS 2025   Slide   Video (35)  

Fast tensor completion via approximate Richardson iteration
Mehrdad Ghadiri, Matthew Fahrbach, Yunbum Kook, Ali Jadbabaie
arXiv   ICML 2025  

Sampling and integration of logconcave functions by algorithmic diffusion
with Santosh S. Vempala
arXiv   STOC 2025   Poster   Slide   Video (40)  

Rényi-infinity constrained sampling with d^3 membership queries
with Matthew S. Zhang
arXiv   SODA 2025   Slide  

In-and-Out: algorithmic diffusion for sampling convex bodies
with Santosh S. Vempala, Matthew S. Zhang
arXiv   [NeurIPS 2024 (Spotlight)]   [Random Structures & Algorithms]   Poster   Slide  

Sampling from the mean-field stationary distribution
with Sinho Chewi, Murat A. Erdogdu, Mufan Bill Li, Matthew S. Zhang
arXiv   COLT 2024   Poster   Slide  

Gaussian cooling and Dikin walks: the interior-point method for logconcave sampling
with Santosh S. Vempala
arXiv   COLT 2024   Poster   Slide  

Understanding Adam optimizer via online learning of updates: Adam is FTRL in disguise
Kwangjun Ahn, Zhiyu Zhang, Yunbum Kook, Yan Dai
arXiv   ICML 2024   Video (15)  

Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integrators
with Yin Tat Lee, Ruoqi Shen, Santosh S. Vempala
arXiv   COLT 2023   Poster   Slide  

Sampling with Riemannian Hamiltonian Monte Carlo in a constrained space
with Yin Tat Lee, Ruoqi Shen, Santosh S. Vempala
arXiv   NeurIPS 2022   Poster   Slide   Code  

Vertex sparsification for edge connectivity
with Parinya Chalermsook, Syamantak Das, Bundit Laekhanukit, Yang P. Liu, Richard Peng, Mark Sellke, Daniel Vaz
arXiv  SODA 2021  Slide   Video(11)   Video(25)   Video(60)  

Evolution of real-world hypergraphs: patterns and models without oracles (long)
Yunbum Kook, Jihoon Ko, Kijung Shin
arXiv   ICDM 2020   [Knowledge and Information Systems]   Slide   Video(20)   Code  

Incremental lossless graph summarization
Jihoon Ko*, Yunbum Kook*, Kijung Shin
arXiv   KDD 2020   Slide   Video(20)   Code  

Template