My research lies at the intersection of applied mathematics, optimal control, and machine learning. I focus on Hamilton–Jacobi–Bellman (HJB) and Hamilton–Jacobi–Isaacs (HJI) equations that arise in stochastic optimal control, differential games, and risk-sensitive decision-making. By combining rigorous PDE theory with physics-informed neural networks (PINNs), I develop neural policy iteration frameworks that overcome the curse of dimensionality while retaining theoretical guarantees.
Bridging viscosity solutions, HJB/HJI equations, PINNs, and operator learning for high-dimensional scientific computing.
(with J. Lee) Hamilton--Jacobi based policy-iteration via deep operator learning, Neurocomputing, 2025.
(with N. Cho, Y. Kim, K. Kim) Physics-informed approach for exploratory Hamilton--Jacobi--Bellman equations via policy iterations, AAAI, 2026.
(with M. Gim, H. Yang) Solving nonconvex Hamilton--Jacobi--Isaacs equations with PINN-based policy iteration, Journal of Scientific Computing, 2026.
(with Y. Park, M. Kim) Acceleration of grokking in learning arithmetic operations via Kolmogorov-Arnold representation, Neurocomputing, 2025.
(with N. Cho, M. Kim, Y. Kim) Physics-informed policy iteration for high-dimensional Hamilton–Jacobi–Bellman equations: Interior error bounds without boundary data, submitted.
(with D. Lee, M. Kim, S. Son) A physics-informed, global-in-time neural particle method for the spatially homogeneous Landau equation, submitted.
(with M. Gim, H. Yang) Certified approximation of probabilistic reachable sets via parabolic Hamilton--Jacobi--Isaacs Equations, submitted.
(with M. Kim, Y. Kim, N. Cho) Monotone neural policy iteration for high-dimensional first-order Hamilton--Jacobi--Bellman equations, submitted.
(with Y. Park) Structure-preserving neural approximation of convex, semiconvex, and quasiconvex functions, submitted.
(with H. Yang) Finite-difference neural policy iteration for high-dimensional degenerate Hamilton--Jacobi equations, submitted.
Rigorous regret analysis, sequential decision-making under uncertainty, and robust policy optimization.
(with K. Jun, I. Yang) Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs, NeurIPS, 2022.
(with I. Yang) On Representation Formulas for Optimal Control: A Lagrangian Perspective, IET Control Theory & Applications, 2022.
(with K. Kim, I. Yang) On concentration bounds for Bayesian identification of linear non-Gaussian systems, Proceedings of the 62nd IEEE Conference on Decision and Control (CDC), 2023.
(with K. Kim, I. Yang) Approximate Thompson sampling for learning linear quadratic regulators with O(√T) regret, Learning for Dynamics & Control Conference (L4DC, Oral Presentation), 2025.
(with Y. Kim, K. Jun) Instance-dependent fixed-budget pure exploration in reinforcement learning, ICLR, 2026 (ICML EXAIT Workshop, 2025).
(with Y. Kim, J. Jang) Penalty-uniform localization for state-constrained policy iteration, submitted.
(with M. Gim, H. Yang) Continuous-time Wasserstein distributionally robust control: Limits, duality, and stability, submitted.
(with K. Lee) Dissipation-based sensitivity bounds for comparing controllers with truncated simulation histories, submitted.
AI-driven topology optimization, grid and energy management, quantitative finance, and facility logistics.
(with T. Costa, J. Cummings, M. Jenkinson, J. Martinez, N. Olivares, A. Sezginer) Fast calculation of diffraction by photomasks, University of Minnesota, IMA, 2014.
(with J. Shin, A. Hakobyan, M. Park, G. Kim, I. Yang) Infusing model predictive control into meta-reinforcement learning for mobile robots in dynamic environments, IEEE Robotics and Automation Letters, 2022.
(with Y. Choi, K. Park) Deep reinforcement learning for optimal design of compliant mechanisms based on digitized cell structures, Engineering Applications of Artificial Intelligence, 2025.
(with K. Park, E. Kim) A human-guided generative model based on diffusion processes for topology optimization, Journal of Computational Design and Engineering, 2026.
(with H. Shin, J. Kim, Y. Koh, H. Kim) Unbalanced optimal transport for efficient visual document retrieval, ECCV, 2026.
(with J. M. Dolot, H. Song) Developing AI voltage stability margin estimation models for voltage stability constrained optimal power flow, Journal of Electrical Engineering & Technology, 2026.
(with S. Choi, K. Kim) A diffusion-based generative model for financial time-series via geometric Brownian motion, submitted.
(with S. Jeong, J. Huh) Computable welfare bounds for constrained dynamic portfolio choice, submitted.
(with S. Jeong, J. Huh) Neural policy iteration for non-homothetic portfolio optimization: residual accuracy and policy performance, submitted.
(with K. Park, Y. Choi) Transferable reinforcement learning for targeted deformation shaping in functionally graded lattice structures, submitted.
(with Y. Park) Covariance-aware warm starts for conditional diffusion, submitted.
(with S. Jeong, J. Huh) Self-consistent adjoint policy iteration for constrained dynamic portfolio choice, submitted.
(with K. Lee) How much of a feasible layout to rebuild: certificate-preserving operator portfolios for dense facility layout under a time budget, submitted.
Battery dispatch under discontinuous tariffs: Tariff-aware rules, value learning, and budgeted mixed-integer control, submitted.
(with D. Kwon, G. Montufar, I. Yang) Training Wasserstein GANs without gradient penalties, preprint.
Fundamental viscosity solution theory, state-constrained boundary problems, and epidemiological control dynamics.
Constrained Hamilton--Jacobi equations and further applications via optimal control theory, Ph.D. Thesis, 2019.
Well-posedness for constrained Hamilton--Jacobi equations, Acta Applicandae Mathematicae, 2020.
On uniqueness for one-dimensional constrained Hamilton--Jacobi equation, Minimax Theory and its Applications, 2020.
(with H. V. Tran, S. N.T. Tu) State-constraint static Hamilton-Jacobi equations in nested domains, SIAM Journal on Mathematical Analysis, 2020.
(with J. Jang) On a minimum eradication time for the SIR model with time-dependent coefficients, Proceedings of the AMS, 2025.
(with Y. Kim, M. Kim) Physics-Informed Neural Networks for optimal vaccination plan in SIR epidemic models, Mathematical Biosciences and Engineering, 2025.
(with N. Cho) On the stability of Lipschitz continuous control problems and its application to reinforcement learning, Advances in Continuous and Discrete Models, 2026.
(with N. Cho) Policy iteration for stationary discounted Hamilton--Jacobi--Bellman equations: A viscosity approach, submitted.
(with Y. Park, J. Jang) Time-optimal vaccination in state-dependent SIR models: a single switch criterion and numerical examples outside its regime, submitted.
(with M. Kim, H. Yang) Minimum-time vaccination for sustained suppression with Erlang infectious periods, submitted.
(with S. Seo, B. Choi) Moreau--Yosida penalization of McKean--Vlasov Dynamics: Full-flux limits and boundary reaction measures, submitted.
Efficiency of a posteriori error bounds based on inf-convolution for Hamilton–Jacobi equations, submitted.