paper-with-me

Papers

Efficient Integrators for Diffusion Generative Models

2023-10-11 · Kushagra Pandey, Maja Rudolph, Stephan Mandt

Diffusion models suffer from slow sample generation at inference time. Therefore, developing a principled framework for fast deterministic/stochastic sampling for a broader class of diffusion models is a promising direction. We propose two complementary frameworks for accelerating sample generation in pre-trained models: Conjugate Integrators and Splitting Integrators. Conjugate integrators generalize DDIM, mapping the reverse diffusion dynamics to a more amenable space for sampling. In contrast, splitting-based integrators, commonly used in molecular dynamics, reduce the numerical simulation error by cleverly alternating between numerical updates involving the data and auxiliary variables. After extensively studying these methods empirically and theoretically, we present a hybrid method that leads to the best-reported performance for diffusion models in augmented spaces. Applied to Phase Space Langevin Diffusion [Pandey & Mandt, 2023] on CIFAR-10, our deterministic and stochastic samplers achieve FID scores of 2.11 and 2.36 in only 100 network function evaluations (NFE) as compared to 2.57 and 2.63 for the best-performing baselines, respectively. Our code and model checkpoints will be made publicly available at \url{https://github.com/mandt-lab/PSLD}.

📄 PDF Abstract BibTeX arXiv:2310.07894

Code (1)

mandt-lab/PSLD 공식 구현 pytorch

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

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 Split…

Denoising MCMC for Accelerating Diffusion-Based Generative Models

2022-09-29 · Beomsu Kim, Jong Chul Ye

Diffusion models are powerful generative models that simulate the reverse of diffusion processes using score functions to synthesize data from noise. The sampling process of diffusion models can be interpreted as solving…

DenoisingImage Generation

Verlet Flows: Exact-Likelihood Integrators for Flow-Based Generative Models

2024-05-05 · Ezra Erives, Bowen Jing, Tommi Jaakkola

Approximations in computing model likelihoods with continuous normalizing flows (CNFs) hinder the use of these models for importance sampling of Boltzmann distributions, where exact likelihoods are required. In this work…

On the Robustness of Distribution Support under Diffusion Guidance

2026-05-08 · Ruijia Cao, Yuchen Wu, Nisha Chandramoorthy arxiv

Diffusion guidance is a powerful technique that enables controllable and high-fidelity sample generation with diffusion models. At a high level, it modifies the score function by incorporating a guidance term that steers…

Robust and Scalable SDE Learning: A Functional Perspective

2021-10-11 · ICLR 2022 4 · Scott Cameron, Tyron Cameron, Arnu Pretorius, Stephen Roberts

Stochastic differential equations provide a rich class of flexible generative models, capable of describing a wide range of spatio-temporal processes. A host of recent work looks to learn data-representing SDEs, using ne…