Functional tensor trains plus BSDE regression solve the HJB score PDE, yielding a fast low-rank sampler that outperforms neural diffusion methods on multimodal targets.
Zhekun Shi, Longlin Yu, Tianyu Xie, and Cheng Zhang
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes. However, accurately estimating the drift term in the reverse stochastic differential equation (SDE) solely from the unnormalized target density poses significant challenges, hindering existing methods from achieving state-of-the-art performance. In this paper, we introduce the Diffusion-PINN Sampler (DPS), a novel diffusion-based sampling algorithm that estimates the drift term by solving the governing partial differential equation of the log-density of the underlying SDE marginals via physics-informed neural networks (PINN). We prove that the error of log-density approximation can be controlled by the PINN residual loss, enabling us to establish convergence guarantees of DPS. Experiments on a variety of sampling tasks demonstrate the effectiveness of our approach, particularly in accurately identifying mixing proportions when the target contains isolated components.
fields
stat.ML 2years
2026 2representative citing papers
DiffCLF reframes EBM training as supervised classification across noise levels to avoid mode blindness while remaining computationally efficient for generative models.
citing papers explorer
-
Tensor Train Diffusion: Leveraging Low-Rank Structures for High-Dimensional Score-Based Sampling
Functional tensor trains plus BSDE regression solve the HJB score PDE, yielding a fast low-rank sampler that outperforms neural diffusion methods on multimodal targets.
-
A Diffusive Classification Loss for Learning Energy-based Generative Models
DiffCLF reframes EBM training as supervised classification across noise levels to avoid mode blindness while remaining computationally efficient for generative models.