paper-with-me

Papers

Towards Fast Stochastic Sampling in Diffusion Generative Models

2024-02-11 · Kushagra Pandey, Maja Rudolph, Stephan Mandt

Diffusion models suffer from slow sample generation at inference time. Despite recent efforts, improving the sampling efficiency of stochastic samplers for diffusion models remains a promising direction. We propose Splitting Integrators for fast stochastic sampling in pre-trained diffusion models in augmented spaces. Commonly used in molecular dynamics, splitting-based integrators attempt to improve sampling efficiency by cleverly alternating between numerical updates involving the data, auxiliary, or noise variables. However, we show that a naive application of splitting integrators is sub-optimal for fast sampling. Consequently, we propose several principled modifications to naive splitting samplers for improving sampling efficiency and denote the resulting samplers as Reduced Splitting Integrators. In the context of Phase Space Langevin Diffusion (PSLD) [Pandey \& Mandt, 2023] on CIFAR-10, our stochastic sampler achieves an FID score of 2.36 in only 100 network function evaluations (NFE) as compared to 2.63 for the best baselines.

📄 PDF Abstract BibTeX arXiv:2402.07211

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

Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure Modeling

2026-02-19 · Xinghao Dong, Huchen Yang, Jin-long Wu arxiv

Diffusion models recently developed for generative AI tasks can produce high-quality samples while still maintaining diversity among samples to promote mode coverage, providing a promising path for learning stochastic cl…

Diffusion Bridge Implicit Models

2024-05-24 · Kaiwen Zheng, Guande He, Jianfei Chen, Fan Bao 외

Denoising diffusion bridge models (DDBMs) are a powerful variant of diffusion models for interpolating between two arbitrary paired distributions given as endpoints. Despite their promising performance in tasks like imag…

DenoisingDiversityTranslation

Fast Sampling for Flows and Diffusions with Lazy and Point Mass Stochastic Interpolants

2026-02-03 · Gabriel Damsholt, Jes Frellsen, Susanne Ditlevsen arxiv

Stochastic interpolants unify flows and diffusions, popular generative modeling frameworks. A primary hyperparameter in these methods is the interpolation schedule that determines how to bridge a standard Gaussian base m…

Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction

2021-12-09 · CVPR 2022 1 · Hyungjin Chung, Byeongsu Sim, Jong Chul Ye

Diffusion models have recently attained significant interest within the community owing to their strong performance as generative models. Furthermore, its application to inverse problems have demonstrated state-of-the-ar…

compressed sensingImage InpaintingSuper-Resolution

SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models

2023-09-10 · NeurIPS 2023 11 · Shuchen Xue, Mingyang Yi, Weijian Luo, Shifeng Zhang 외

Diffusion Probabilistic Models (DPMs) have achieved considerable success in generation tasks. As sampling from DPMs is equivalent to solving diffusion SDE or ODE which is time-consuming, numerous fast sampling methods bu…

Image Generation