Papers in Progress
Papers in Progress
Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting, with Hojin Ko
Recovering the Kinks in Delay Control: A Structure-Aware RL Approach via Pontryagin Projection, with Ji-Hun Kim
Finite Horizon and Optimal Portfolio Choice with Stochastic Income: A Reinforcement Learing Approach, with Seyoung Park, Hojin Ko, Alain Bensoussan
From AlphaGo to PGDPO: How Neural Networks Learn Adjoint Dynamics, with Hyeng-Keun Koo, Alain Bensoussan
Deep Arbitrage Pricing Theory: Disentangling Myopic and Intertemporal Hedging Demands, with Seungwon Jeong
End-to-End Learning of Asset Betas for Sharpe-Optimal Portfolios, with Dongwan Shin
PPC: Pontryagin Predictor-Corrector for Generative Control, with Ji-Hun Kim, Hojin Ko
Physics-Informed Deep Operator Learning for Finite-Horizon Stochastic Optimal Control, with Jung Min Lee, Seungwon Jeong, Yeoneung Kim
Deep Operator Learning for Forecasting Multi-scale Implied Volatility Surfaces, with Minji Lee
Adversarial Time-Series Domain Adaptation for Early-Stage IPO Price Prediction, with Youngwoo Lee
Learning the Black-Scholes Operator: Handling Time-Dependent Parameters via Deep Neural Operators, with Myeongsik Kim
Pricing the Portfolio Cube: Deep Operator Learning for Dynamic Structured Product Books, with Yoonyoung Byun
Scalable Deep Hedging: Breaking the Curse of Dimensionality in High-Dimensional Portfolios, with Seungho Na
Universal Deep Hedging: A Deep Operator Learning Approach, with Seungho Na
MarketGANs: Multivariate financial time-series data augmentation using generative adversarial networks, with Seungwon Jeong, Hyun-Gyoon Kim, Hyeng Keun Koo, Byung Hwa Lim
Beyond its current scope, PG-DPO admits natural extensions to partial equilibrium settings—including transaction costs, taxation, Epstein-Zin utility, and belief-state dynamics—as well as general equilibrium frameworks such as mean-field control and games in finance."