Working Papers

• MarketGANs: Multivariate Financial Time-Series Data Augmentation Using Generative Adversarial Networks, with Hyeng-Keun Koo, Byung Hwa Lim,  Hyun-Gyoon Kim

• Breaking the Dimensional Barrier for Continuous-Time Time-Inconsistent Control, with Hyeng-Keun Koo, Byung Hwa Lim

• A Unified Framework Linking Deep Learning and Optimal Control: Backpropagation Realizes Pontryagin’s Principle, with Hyeng-Keun Koo [GitHub]

• Breaking the Dimensional Barrier in Dynamic Portfolio Choice with Transaction Costs

• Breaking the Dimensional Barrier in Dynamic Portfolio Choice with Taxes 

*  Beyond its current scope, PG-DPO may admit natural extensions to  1) mean-field control, 2) optimal stopping, 3) robust control, 4) EZ utility, 5) mean-field games, and 6) multi-agent frameworks.