Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization

• URL: http://arxiv.org/abs/2608.18040v1
• Date: Tue, 18 Aug 2026 17:33:00 GMT
• Title: Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization
• Abstract summary: We treat timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization.<n>OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks.<n>A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.
• Score: 38.696490789425006
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on efficient solvers and samplers, comparatively little attention has been paid to selecting the sampling timesteps themselves. A recent line of work optimizes theoretically derived surrogates for sample quality rather than the quality metric itself. We propose Optimizing Your Sampling (OYS), which instead treats timestep selection as a black-box optimization problem, optimizing the target metric directly with Bayesian optimization. OYS outperforms both the default schedules and those of Align Your Steps on text-to-image generation, and improves over the default schedules on inpainting and other image tasks, in both quantitative and human evaluations. OYS requires no additional training, is applicable even to distilled models, and improves both simple and sophisticated samplers such as Euler and DPM-Solver++. A 5-step OYS schedule retains 89%-94% of the quality of a 50-step schedule while reducing inference cost by 10x.

Related papers

• Autocorrelated Optimize-via-Estimate: Predict-then-Optimize versus Finite-sample Optimal [2.0228793142608588]
  Models that directly optimize for out-of-sample performance in the finite-sample regime have emerged as a promising alternative to traditional estimate-then-optimize approaches.<n>We compare their performance in the context of autocorrelated uncertainties, specifically, under a Vector Autoregressive Moving Average VARMA(p,q) process.
  arXiv  Detail & Related papers  (2026-02-02T09:49:51Z)
• Hyperparameter Transfer Enables Consistent Gains of Matrix-Preconditioned Optimizers Across Scales [55.91454326946738]
  We study how the optimal learning rate and weight decay should scale with model width and depth for a wide range of languages.<n>We find that scaling the learning rate according to $$P improves transfer, but can still suffer from significant finite-width deviations.<n>For compute-optimal scaling, we find scaling independent weight decay as $1/mathrmwidth$ is nearly optimal across languages.
  arXiv  Detail & Related papers  (2025-12-05T11:03:41Z)
• Beyond Outliers: A Study of Optimizers Under Quantization [82.75879062804955]
  We study impact of choice on model robustness under quantization.<n>We evaluate how model performance degrades when trained with different baselines.<n>We derive scaling laws for quantization-aware training under different parameters.
  arXiv  Detail & Related papers  (2025-09-27T21:15:22Z)
• Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimization [37.54165341391688]
  We introduce a novel problem: Sample Scheduling for DPO.<n>We propose SamS, an efficient and effective algorithm that adaptively selects samples in each training batch.<n>This work points to a promising new direction for improving LLM alignment through batch-wise sample selection.
  arXiv  Detail & Related papers  (2025-06-08T10:26:09Z)
• Simplifying Bayesian Optimization Via In-Context Direct Optimum Sampling [18.852567298468742]
  We propose a completely in-context zero-shot solution for BO that does not require surrogate fitting or acquisition function optimization.<n>This is done by using a pre-trained context model to directly sample from the posterior over the optimum point.<n>We achieve an efficiency gain of more than 35x in terms of wall-clock time when compared with process-based BO.
  arXiv  Detail & Related papers  (2025-05-29T18:07:36Z)
• Satori-SWE: Evolutionary Test-Time Scaling for Sample-Efficient Software Engineering [51.7496756448709]
  Language models (LMs) perform well on coding benchmarks but struggle with real-world software engineering tasks.<n>Existing approaches rely on supervised fine-tuning with high-quality data, which is expensive to curate at scale.<n>We propose Test-Time Scaling (EvoScale), a sample-efficient method that treats generation as an evolutionary process.
  arXiv  Detail & Related papers  (2025-05-29T16:15:36Z)
• Efficient NeRF Optimization -- Not All Samples Remain Equally Hard [9.404889815088161]
  We propose an application of online hard sample mining for efficient training of Neural Radiance Fields (NeRF) NeRF models produce state-of-the-art quality for many 3D reconstruction and rendering tasks but require substantial computational resources.
  arXiv  Detail & Related papers  (2024-08-06T13:49:01Z)
• 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)

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.