Minseok Jeong

Hi, I am Minseok Jeong, a Ph.D. student at the KAIST ACSS Lab under the supervision of Prof. SooJean Han. I received my B.E. in System Management Engineering (Industrial Engineering) from SKKU, and my M.S. in Electrical and Electronic Engineering from GIST, where I worked in the IIS Lab with Prof. Euiseok Hwang.

My research focuses on understanding complex stochastic dynamical systems through data-driven approaches.

I am particularly interested in how the desirable properties of stochastic systems can be exploited across different subfields:

Machine Learning & Optimization: randomized algorithms such as Langevin dynamics and randomized embeddings
Decision Making under Uncertainty: conformal prediction and reinforcement learning
Linearization Methods: linear MDP, kernel method and Koopman operator theory

news

Sep 18, 2025	NeurIPS 2025, Spotlight Presentation 🎉 “Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics” (688 out of 21,575 submissions, top 3.2%)

selected publications

In press

Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics

Minseok Jeong^*, Giup Seo^*, and Euiseok Hwang

In Proceedings of the Conference on Neural Information Processing Systems (NeurIPS), 2025

Spotlight Presentation

Abs

Recently, physics-informed neural networks (PINNs) have gained attention in the scientific community for their potential to solve partial differential equations (PDEs). However, they face challenges related to resource efficiency and slow convergence. Adaptive sampling methods, which prioritize collocation points with high residuals, improve both efficiency and accuracy. However, these methods often neglect points with medium or low residuals, which can affect stability as the complexity of the model increases. In this paper, we investigate this limitation and show that high residual-based approaches require stricter learning rate bounds to ensure stability. To address this, we propose a Langevin dynamics-based Adaptive Sampling (LAS) framework that is robust to various learning rates and model complexities. Our experiments demonstrate that the proposed method outperforms existing approaches in terms of relative error, and stability across a range of enviroments, including high-dimensional PDEs where Monte Carlo integration-based methods typically suffer from instability.