Youngkyu Lee (이영규)

I am an Assistant Professor in Department of Mathematics at Kyung Hee University. Previously, I was a postdoctoral researcher in Applied Mathematics at Brown University (CRUNCH Group led by Prof. George Karniadakis). I received a Ph.D. degree in Mathematcial Sciences in 2023 (Advisor: Chang-Ock Lee) from KAIST.

My research interests include computational mathematics, parallel computation, and scientific machine learning, agentic AI. I am particularly interested in developing the preconditioners to accelerate the neural or numerical solvers for scientific problems.

Curriculum Vitae, Google Scholar

Education

• Ph. D. Mathematical Sciences, August 2023, KAIST, South Korea
  Advisor: Chang-Ock Lee

• B.S. Mathematics, February 2017, Kyung Hee University, South Korea

Publication

Submitted papers

1. Jaemin Oh, Youngkyu Lee, Jerome Darbon, and George Em Karniadakis. Spectrally Safe Neural Operator Warm-Starts for Large-Scale Newton Solvers (2026). arXiv

2. Francesc Levrero Florencio, Youngkyu Lee,  Jay Pathak, and George Em Karniadakis. NSPOD: Accelerating Krylov solvers via DeepONet-learned POD subspaces (2026). arXiv

3. Shanqing Liu, Paula Chen, Youngkyu Lee, and Jerome Darbon. Algorithms and Differential Game Representations for Exploring Nonconvex Pareto Fronts in High Dimensions (2026). arXiv

4. Youngkyu Lee, Shanqing Liu, Jerome Darbon, and George Em Karniadakis. A Neural-Operator Preconditioned Newton Method for Accelerated Nonlinear Solvers (2025). arXiv

Published/Accepted papers

1. Youngkyu Lee, Shanqing Liu, Jerome Darbon, and George Em Karniadakis. Automatic discovery of optimal meta-solvers for time-dependent nonlinear PDEs. To appear in Journal of Computational Physics. arXiv

2. Youngkyu Lee,  Francesc Levrero Florencio, Jay Pathak, and George Em Karniadakis. Hybrid Iterative Solvers with Geometry-Aware Neural Preconditioners for Parametric PDEs. International Journal for Numerical Methods in Engineering, 127, no. 15, e70393 (2026). link arXiv

3. Youngkyu Lee, Shanqing Liu, Jerome Darbon, and George Em Karniadakis. Automatic discovery of optimal meta-solvers via multi-objective optimization. Journal of Computational Physics, 563, 115015 (2026). link arXiv

4. Shilaj Baral, Youngkyu Lee, Sangam Khanal, Joongoo Jeon. XRePIT: A deep learning–computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations. Computers & Fluids, 314, 107075 (2026). link arXiv

5. Alena Kopaničáková, Youngkyu Lee, and George Em Karniadakis. Leveraging Operator Learning to Accelerate Convergence of the Preconditioned Conjugate Gradient Method. Mach. Learn. Comput. Sci. Eng, 1, 39 (2025). link arXiv

6. Youngkyu Lee, Alena Kopaničáková, and George Em Karniadakis. Two-level Overlapping Additive Schwarz Preconditioners for Training Scientific Machine Learning Applications. Computer Methods in Applied Mechanics and Engineering, 448, 118400 (2026). link arXiv

7. Youngkyu Lee, Jongho Park, and Chang-Ock Lee. Balanced group convolution: An improved group convolution based on approximability estimates. Pattern Anal Applic 28, 161 (2025). link arXiv

8. Sunwoong Yang, Youngkyu Lee, and Namwoo Kang. Data-efficient deep operator network for unsteady flow: A multi-fidelity approach with physics-guided subsampling. Computer Methods in Applied Mechanics and Engineering, 446, 118254 (2025). link arXiv

9. Youngkyu Lee, Shanqing Liu, Zongren Zou, Adar Kahana, Eli Turkel, Rishikesh Ranade, Jay Pathak, and George Em Karniadakis. Fast meta-solvers for 3D complex-shape scatterers using neural operators trained on a non-scattering problem. Computer Methods in Applied Mechanics and Engineering, 446, 118231 (2025). link arXiv

10. Chang-Ock Lee, Youngkyu Lee, and Byungeun Ryoo. A Nonoverlapping Domain Decomposition Method for Extreme Learning Machines: Elliptic Problems. Computers and Mathematics with Applications, 189, 109–128 (2025). link arXiv

11. Youngkyu Lee,  Jongho Park, and Chang-Ock Lee. Parareal neural networks emulating a parallel-in-time algorithm. IEEE Transactions on Neural Networks and Learning Systemsm, 35, 6353–6364 (2024). link arXiv

12. Chang-Ock Lee, Youngkyu Lee, and Jongho Park. A parareal architecture for very deep neural network. Domain Decomposition Methods in Science and Engineering XXVI, 407–415, Lecture Notes in Computational Science and Engineering, 145, Springer, 2023. link

13. Youngkyu Lee,  Jongho Park, and Chang-Ock Lee. Two-level group convolution. Neural Networks, 154, 323–332 (2022). link arXiv

Teaching Experiences

1. Fall 2026 Applied Mathematics

2. Fall 2026 Topics in Applied Mathematics 2 (Graduate course)