$\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models

• URL: http://arxiv.org/abs/2410.07761v1
• Date: Thu, 10 Oct 2024 09:44:25 GMT
• Title: $\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models
• Authors: Yong-Hyun Park, Chieh-Hsin Lai, Satoshi Hayakawa, Yuhta Takida, Yuki Mitsufuji,
• Abstract summary: We present $textitJump Your Steps$ (JYS), a novel approach that optimize the allocation of discrete sampling timesteps by minimizing CDE without extra computational cost. In experiments across image, music, and text generation, JYS significantly improves sampling quality.
• Score: 16.738569359216438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have seen notable success in continuous domains, leading to the development of discrete diffusion models (DDMs) for discrete variables. Despite recent advances, DDMs face the challenge of slow sampling speeds. While parallel sampling methods like $\tau$-leaping accelerate this process, they introduce $\textit{Compounding Decoding Error}$ (CDE), where discrepancies arise between the true distribution and the approximation from parallel token generation, leading to degraded sample quality. In this work, we present $\textit{Jump Your Steps}$ (JYS), a novel approach that optimizes the allocation of discrete sampling timesteps by minimizing CDE without extra computational cost. More precisely, we derive a practical upper bound on CDE and propose an efficient algorithm for searching for the optimal sampling schedule. Extensive experiments across image, music, and text generation show that JYS significantly improves sampling quality, establishing it as a versatile framework for enhancing DDM performance for fast sampling.

Related papers

• Score-based Generative Models with Adaptive Momentum [40.84399531998246]
  We propose an adaptive momentum sampling method to accelerate the transforming process. We show that our method can produce more faithful images/graphs in small sampling steps with 2 to 5 times speed up.
  arXiv  Detail & Related papers  (2024-05-22T15:20:27Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Align Your Steps: Optimizing Sampling Schedules in Diffusion Models [63.927438959502226]
  Diffusion models (DMs) have established themselves as the state-of-the-art generative modeling approach in the visual domain and beyond. A crucial drawback of DMs is their slow sampling speed, relying on many sequential function evaluations through large neural networks. We propose a general and principled approach to optimizing the sampling schedules of DMs for high-quality outputs.
  arXiv  Detail & Related papers  (2024-04-22T18:18:41Z)
• Accelerating Diffusion Sampling with Optimized Time Steps [69.21208434350567]
  Diffusion probabilistic models (DPMs) have shown remarkable performance in high-resolution image synthesis. Their sampling efficiency is still to be desired due to the typically large number of sampling steps. Recent advancements in high-order numerical ODE solvers for DPMs have enabled the generation of high-quality images with much fewer sampling steps.
  arXiv  Detail & Related papers  (2024-02-27T10:13:30Z)
• Accelerating Parallel Sampling of Diffusion Models [25.347710690711562]
  We propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms by a factor of 4$sim$14 times.
  arXiv  Detail & Related papers  (2024-02-15T14:27:58Z)
• Semi-Implicit Denoising Diffusion Models (SIDDMs) [50.30163684539586]
  Existing models such as Denoising Diffusion Probabilistic Models (DDPM) deliver high-quality, diverse samples but are slowed by an inherently high number of iterative steps. We introduce a novel approach that tackles the problem by matching implicit and explicit factors. We demonstrate that our proposed method obtains comparable generative performance to diffusion-based models and vastly superior results to models with a small number of sampling steps.
  arXiv  Detail & Related papers  (2023-06-21T18:49:22Z)
• Preconditioned Score-based Generative Models [49.88840603798831]
  An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We propose a model-agnostic bfem preconditioned diffusion sampling (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. PDS alters the sampling process of a vanilla SGM at marginal extra computation cost, and without model retraining.
  arXiv  Detail & Related papers  (2023-02-13T16:30:53Z)
• Fast Inference in Denoising Diffusion Models via MMD Finetuning [23.779985842891705]
  We present MMD-DDM, a novel method for fast sampling of diffusion models. Our approach is based on the idea of using the Maximum Mean Discrepancy (MMD) to finetune the learned distribution with a given budget of timesteps. Our findings show that the proposed method is able to produce high-quality samples in a fraction of the time required by widely-used diffusion models.
  arXiv  Detail & Related papers  (2023-01-19T09:48:07Z)
• Denoising Diffusion Implicit Models [117.03720513930335]
  We present denoising diffusion implicit models (DDIMs) for iterative implicit probabilistic models with the same training procedure as DDPMs. DDIMs can produce high quality samples $10 times$ to $50 times$ faster in terms of wall-clock time compared to DDPMs.
  arXiv  Detail & Related papers  (2020-10-06T06:15:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.