7 papers
Adaptive Reparametrized Time for Score-Based Diffusion Sampling
Yilie Huang, Wenpin Tang, Xun Yu Zhou
We study timestep allocation for score-based diffusion sampling, where a learned reverse-time dynamics is discretized on a finite grid. Uniform and hand-crafted schedules are stand…
Image AID via continuous-time reinforcement learning
Yilie Huang, Xun Yu Zhou
We study image inpainting with generative diffusion models. Existing methods typically either train dedicated task-specific models, or adapt a pretrained diffusion model separately…
ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Schedule
Yilie Huang, Wenpin Tang, Xunyu Zhou
We consider time discretization for score-based diffusion models to generate samples from a learned reverse-time dynamic on a finite grid. Uniform and hand-crafted grids can be sub…
Continuous-Time Reinforcement Learning for Asset-Liability Management
Yilie Huang
This paper proposes a novel approach for Asset-Liability Management (ALM) by employing continuous-time Reinforcement Learning (RL) with a linear-quadratic (LQ) formulation that inc…
Data-Driven Exploration for a Class of Continuous-Time Indefinite Linear--Quadratic Reinforcement Learning Problems
Yilie Huang, Xun Yu Zhou
We study reinforcement learning (RL) for the same class of continuous-time stochastic linear--quadratic (LQ) control problems as in \cite{huang2024sublinear}, where volatilities de…
Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study
Yilie Huang, Yanwei Jia, Xun Yu Zhou
We study continuous-time mean--variance portfolio selection in markets where stock prices are diffusion processes driven by observable factors that are also diffusion processes, ye…
Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems
Yilie Huang, Yanwei Jia, Xun Yu Zhou
We study reinforcement learning (RL) for a class of continuous-time linear-quadratic (LQ) control problems for diffusions, where states are scalar-valued and running control reward…