• Ph.D., Cornell University, August 1999

• B.S., Seoul National University , August 1993

• My research focuses on the design and analysis of reliable, efficient, and mathematically grounded methods for learning, optimization, inference, and decision-making, with two major research directions: Industrial & Physical AI Safety and Digital Finance.

• The mathematical foundations of my research have been built around three closely connected areas: global optimization, dynamical systems, and statistical learning. My early work investigated stability analysis of nonlinear dynamical systems, equilibrium characterization, convergence of optimization algorithms, and trajectory-based global optimization. A recurring theme has been the close relationship between optimality and equilibrium, using dynamical-system perspectives to solve optimization and learning problems, while applying optimization, numerical, and topological methods to analyze complex nonlinear systems. 

• Building on these foundations, my research expanded into stable and robust machine learning, including support vector machines, kernel methods, Gaussian processes, clustering, representation learning, domain adaptation, forecasting, and data-driven decision-making. More recently, this work has increasingly addressed broader Trustworthy AI challenges, including robustness, privacy, fairness, security, stability, explainability, and verification. 

• In parallel, I have applied these mathematical and learning-based methodologies to computational and digital finance, including derivative pricing, financial forecasting, model calibration, portfolio optimization, risk management, and data-driven financial modeling. 

• My current and emerging research brings these foundations together in two major directions.

Industrial & Physical AI Safety

• • Building on my research in AI safety, robust learning, optimization, and dynamical systems, I am extending these foundations toward Industrial & Physical AI Safety, the development of AI systems that can operate safely and reliably in industrial processes and physical environments. 

  • The research spans the full closed-loop intelligence workflow: robust perception and state estimation, predictive process and world models, safe planning and robust decision-making, stable control and verified optimization, and runtime safety assurance and explainability. Particular attention is given to uncertainty, distribution shift, adversarial perturbations, sensor and process failures, stability, safe operating regions, and human-interpretable intervention. 

  • A central objective is to combine learning-based methods with rigorous mathematical systems analysis, connecting modern AI with stability analysis, robustness guarantees, optimization, verification, and runtime assurance. Simulation and generative modeling are used to construct rare and safety-critical scenarios, while real-world and industrial validation provide the basis for evaluating whether learned systems remain reliable under realistic operating conditions. 

  • Underlying these efforts is a system-wide Trustworthy AI foundation encompassing robustness and security, stability and verification, privacy preservation, fairness, and explainability. Rather than treating safety as a property evaluated only before deployment, my research views safety as a requirement that must be maintained throughout the entire lifecycle of an intelligent system. 

Digital Finance

• • My research in Digital Finance integrates artificial intelligence, computational finance, optimization, blockchain, and generative modeling to develop intelligent, reliable, and secure financial systems. 

  • The research covers financial forecasting, asset and derivative pricing, portfolio optimization, risk management, decentralized finance, digital financial infrastructure, and AI-driven financial decision-making. It combines mathematical finance and statistical learning with modern machine-learning approaches to address complex financial systems characterized by uncertainty, nonstationarity, limited observations, and rapidly changing market conditions. 

  • An important emerging direction is to move beyond conventional prediction based solely on historical data toward generative and simulation-based financial intelligence. The goal is to develop models capable of generating plausible market scenarios, evaluating alternative strategies and policy interventions, stress-testing financial decisions, and supporting robust decision-making under uncertainty. 

  • Across both research directions, the overarching goal is to connect mathematical foundations, trustworthy machine learning, optimization, and domain-specific intelligence to develop AI systems that are not only effective, but also robust, stable, secure, explainable, and trustworthy in real-world operation. 

Industrial & Physical Ai safety

Safe Industrial & & Physical AI 

• Robust Perception & State Estimation 

• Predictive Process & World Models

• Safe Planning & Robust Decision Making 

• Stable Control & Verified Optimization 

• Runtime Safety Assurance & Explainability 

Trustworthy ai foundations

• Privacy-Preserving & Fair AI 

• Stable & Robust Machine Learning 

• Data-Centric AI Engineering

Digital Finance

Financial AI & Computational Finance

• Financial Intelligence & Market Forecasting

• Computational Finance & Asset Pricing

• Intelligent Portfolio & Risk Management

Digital assets & Blockchain

• Blockchain, Digital Assets & Decentralized Finance

• Secure Finance Infrastructure & Digital Payments

Honors & Professional Leadership 

• Member of the National Academy of Engineering of Korea - Computer Science and Engineering

• Fellow and Board member: Asia Pacific Industrial Engineering and Management Society (APIEMS)

• Leader, Privacy-Preserving Convergence Technology Working Group (2021)

Editorial Service 

• Associate Editor, Applied Stochastic Models in Business and Industry

• Managing Editor/ Manuscript Editor, Journal of Industrial Engineering and Management Systems (2009 - 2023)

• Editor-in-Chief, Management Science and Financial Engineering (2012 – 2014)

• Guest / Associate Editor for Journal of Intelligent Manufacturing, Decision Sciences, and International Journal of Management Science (2005 – 2011)

Conference Service

• Organizing Chair, APIEMS 2014

• General Organizing Chair, International Workshop on Learning, Computations, and Finance (LCF 2010)

• Programmer Committee Member for international data-mining conferences

Reviewing Activities

• Area Chair and/or Paper Reviewer for major AI conferences including NeurIPS, ICML, ICLR, CVPR, AAAI and KDD

• Reviewer for leading journals in AI, machine learning, control, optimization, finance, and industrial engineering, including IEEE TPAMI, IEEE TNN, IEEE TAC, JMLR, Pattern Recognition, Expert Systems with Applications, Annals of Operations Research, and Journal of Banking & Finance