| 2025 | ICLR | Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes. | Jongmin Lee, Ernest K. Ryu |
| 2025 | ICLR | Encryption-Friendly LLM Architecture. | Donghwan Rho, Taeseong Kim, Minje Park, Jung Woo Kim, Hyunsik Chae, Ernest K. Ryu, Jung Hee Cheon |
| 2025 | ICML | LoRA Training Provably Converges to a Low-Rank Global Minimum Or It Fails Loudly (But it Probably Won't Fail). | Junsu Kim, Jaeyeon Kim, Ernest K. Ryu |
| 2024 | ICLR | Image Clustering Conditioned on Text Criteria. | Sehyun Kwon, Jaeseung Park, Minkyu Kim, Jaewoong Cho, Ernest K. Ryu, Kangwook Lee |
| 2024 | ICML | LoRA Training in the NTK Regime has No Spurious Local Minima. | Uijeong Jang, Jason D. Lee, Ernest K. Ryu |
| 2024 | ICML | Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique. | Taeho Yoon, Jaeyeon Kim, Jaewook J. Suh, Ernest K. Ryu |
| 2023 | ICML | Rotation and Translation Invariant Representation Learning with Implicit Neural Representations. | Sehyun Kwon, Joo Young Choi, Ernest K. Ryu |
| 2023 | ICML | Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations. | Jisun Park, Ernest K. Ryu |
| 2022 | AISTATS | Robust Probabilistic Time Series Forecasting. | Taeho Yoon, Youngsuk Park, Ernest K. Ryu, Yuyang Wang |
| 2022 | ICML | Neural Tangent Kernel Analysis of Deep Narrow Neural Networks. | Jongmin Lee, Joo Young Choi, Ernest K. Ryu, Albert No |
| 2022 | ICML | Exact Optimal Accelerated Complexity for Fixed-Point Iterations. | Jisun Park, Ernest K. Ryu |
| 2022 | ICML | Continuous-Time Analysis of Accelerated Gradient Methods via Conservation Laws in Dilated Coordinate Systems. | Jaewook J. Suh, Gyumin Roh, Ernest K. Ryu |
| 2021 | ICML | WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points. | Albert No, Taeho Yoon, Sehyun Kwon, Ernest K. Ryu |
| 2021 | ICML | Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with O(1/k^2) Rate on Squared Gradient Norm. | Taeho Yoon, Ernest K. Ryu |
| 2019 | ICML | Plug-and-Play Methods Provably Converge with Properly Trained Denoisers. | Ernest K. Ryu, Jialin Liu, Sicheng Wang, Xiaohan Chen, Zhangyang Wang, Wotao Yin |