5 papers
On a Class of Non-Local Elliptic-Transport Systems in Score-Guided Probability Flow on : Score-Singularity Resolution, Space-Time ADN Shift, and Markov Mean-Field Games
Pilhwa Lee
We establish mathematical foundations for optimal spatiotemporal vector fields governing continuous score-guided probability flows over bounded submanifolds on th…
Density-Guided Bootstrap Boundaries for Latent World-Model Reinforcement Learning
Shashank Gupta, Pilhwa Lee
Latent world models allow reinforcement learning agents to learn policies from imagined trajectories, yet determining the optimal depth of model reliance remains a fundamental chal…
Immersed Boundary Electrodiffusion in the Wasserstein Gradient Flow Formalism: Global Well-Posedness, Non-Equilibrium Thermodynamics, and Singular Asymptotics
Pilhwa Lee
We introduce a unified optimal transport framework for the Immersed Boundary (IB) electrodiffusion active pump model. By representing membrane chemical potential barriers and activ…
Liouville PDE-based sliced-Wasserstein flow
Jayshawn Cooper, Pilhwa Lee
The sliced Wasserstein flow (SWF), a nonparametric and implicit generative gradient flow, is transformed into a Liouville partial differential equation (PDE)-based formalism. First…
Meta-reinforcement learning with minimum attention
Shashank Gupta, Pilhwa Lee
Minimum attention applies the least action principle in changes of control concerning state and time, first proposed by Brockett. The involved regularization is highly relevant in…