Viet Vu

collaborators

Showing stat.MLShow all

2 papers · 1 filter

stat.ML2026

Expressivity and Statistical Trade-offs in Diffusion Policy Learning

Viet Vu, Renyuan Xu, Jiacheng Zhang +1

Diffusion-based policies have recently emerged as powerful policy parameterizations for reinforcement learning, representing state-conditioned action distributions as terminal laws…

stat.ML2026

Computational bottlenecks for denoising diffusions

Andrea Montanari, Viet Vu

Denoising diffusions sample from a probability distribution $I^¼$ in $R^{d}$ by constructing a stochastic process $(x^_{t} : t \geq 0)$ in $R^{d}$ such th…