paper-with-me

홈 › Papers

Diffusion-PINN Sampler

2024-10-20 · Zhekun Shi, Longlin Yu, Tianyu Xie, Cheng Zhang

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.

📄 PDF Abstract BibTeX arXiv:2410.15336

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Accelerating Convergence of Score-Based Diffusion Models, Provably

2024-03-06 · Gen Li, Yu Huang, Timofey Efimov, Yuting Wei 외

Score-based diffusion models, while achieving remarkable empirical performance, often suffer from low sampling speed, due to extensive function evaluations needed during the sampling phase. Despite a flurry of recent act…

Towards Faster Non-Asymptotic Convergence for Diffusion-Based Generative Models

2023-06-15 · Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi

Diffusion models, which convert noise into new data instances by learning to reverse a Markov diffusion process, have become a cornerstone in contemporary generative modeling. While their practical power has now been wid…

Denoising

On scalable and efficient training of diffusion samplers

2025-05-26 · Minkyu Kim, Kiyoung Seong, Dongyeop Woo, Sungsoo Ahn 외

We address the challenge of training diffusion models to sample from unnormalized energy distributions in the absence of data, the so-called diffusion samplers. Although these approaches have shown promise, they struggle…

Single-Step Consistent Diffusion Samplers

2025-02-11 · Pascal Jutras-Dubé, Patrick Pynadath, Ruqi Zhang

Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality sample…

Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spaces

2026-02-05 · Arran Carter, Sanghyeok Choi, Kirill Tamogashev, Víctor Elvira 외 arxiv

Sampling from a distribution $p(x) \propto e^{-\mathcal{E}(x)}$ known up to a normalising constant is an important and challenging problem in statistics. Recent years have seen the rise of a new family of amortised sampl…