The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets
We analyze the parameter bounds for robust memorization as a function of the robustness ratio.
🫧My name is Yujun Kim and I am a Master’s student in the Optimization & Machine Learning (OptiML) at KAIST AI. I am interested in optimization and deep learning theory. I finished my undergraduate program in Mathematical Sciences with a double major in School of Computing at KAIST.
Education
M.S. in Artificial Intelligence
Korea Advanced Institute of Science and Technology (KAIST)
B.S. in Mathematical Sciences, B.E. in School of Computing
Korea Advanced Institute of Science and Technology (KAIST)
Korea Science Academy of KAIST (KSA)
Research Interest
I am interested in optimization and deep learning theory. I am currently researching on parameter-free optimization.
Recent News
Incremental Gradient Descent with Small Epoch Counts is Surprisingly Slow on Ill-Conditioned Problems
We study Incremental Gradient Descent in the small epoch regime and show that it exhibits severe slowdown especially in the presence of nonconvex components.
CMY : Color Puzzle Platformer Game
Color Puzzle Platformer Game
Santa Tell Me : OpenGL-based Rhythm Game
OpenGL-based Rhythm Game
Tutoring Calculus
Participated in the KAIST Tutoring program as a tutor for Calculus 1,2.
Featured Publications
Recent Publications
(2025).
The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets.
In HiLD, ICML 2025.
Recent & Upcoming Talks
