paper-with-me

Papers

FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation

2022-10-09 · Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon

Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the Fokker-Planck equation (FPE), a partial differential equation (PDE) governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation called the score FPE that characterizes the noise-conditional scores of the perturbed data densities (i.e., their gradients). Surprisingly, despite the impressive empirical performance, we observe that scores learned through denoising score matching (DSM) fail to fulfill the underlying score FPE, which is an inherent self-consistency property of the ground truth score. We prove that satisfying the score FPE is desirable as it improves the likelihood and the degree of conservativity. Hence, we propose to regularize the DSM objective to enforce satisfaction of the score FPE, and we show the effectiveness of this approach across various datasets.

📄 PDF Abstract BibTeX arXiv:2210.04296

Code (1)

sony/fp-diffusion 공식 구현 jax

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Denoising Score Matching Training a denoiser on signals gives you a powerful prior over this signal that you can then use to sample examples of this signal.
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

Local Mechanisms of Compositional Generalization in Conditional Diffusion

2025-09-19 · Arwen Bradley arxiv

Conditional diffusion models appear capable of compositional generalization, i.e., generating convincing samples for out-of-distribution combinations of conditioners, but the mechanisms underlying this ability remain unc…

Consistent Sampling and Simulation: Molecular Dynamics with Energy-Based Diffusion Models

2025-06-20 · Michael Plainer, Hao Wu, Leon Klein, Stephan Günnemann 외

Diffusion models have recently gained significant attention due to their effectiveness in various scientific domains, including biochemistry. When trained on equilibrium molecular distributions, diffusion models provide …

The Diffusion-Attention Connection

2026-02-11 · Julio Candanedo arxiv

Softmax attention is the row-normalized operator of a diffusion map: both normalize a learned score into a Markov operator, and differ only in what the score is allowed to contain. Decomposing that score reveals three ge…

Towards diffusion models for large-scale sea-ice modelling

2024-06-26 · Tobias Sebastian Finn, Charlotte Durand, Alban Farchi, Marc Bocquet 외

We make the first steps towards diffusion models for unconditional generation of multivariate and Arctic-wide sea-ice states. While targeting to reduce the computational costs by diffusion in latent space, latent diffusi…

Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching

2026-01-10 · Jinyuan Chang, Chenguang Duan, Yuling Jiao, Yi Xu 외 arxiv

Inference-time alignment for diffusion models aims to adapt a pre-trained reference diffusion model toward a target distribution without retraining the reference score network, thereby preserving the generative capacity …