提出首个针对扩散模型的一阶生成式双层优化框架，解决训练与微调中的超参数优化难题。
A First-order Generative Bilevel Optimization Framework for Diffusion Models
- 将扩散模型优化建模为生成式双层问题，设计高效梯度估计器应对无限维空间挑战。
- 在微调和噪声调度优化任务中均显著优于现有方法，实现更高质量的生成结果。
- 适合需要高效超参数搜索或微调扩散模型的研究者与工程师使用。
扩散模型通过迭代去噪生成高质量数据，在多个领域取得成功。然而，针对下游任务优化这些模型常涉及嵌套的双层结构，如微调时调整超参数或训练中优化噪声调度，传统双层方法因无限维概率空间和高昂采样成本而失效。本文将此问题形式化为生成式双层优化，并解决两个关键场景：(1) 采用仅推理的下层求解器与样本高效的上层梯度估计器微调预训练模型；(2) 从零训练扩散模型时，通过重参数化下层问题并设计计算可行的梯度估计器优化噪声调度。所提一阶双层框架克服了传统方法与扩散过程不兼容的问题，兼具理论基础与计算可行性。实验表明，该方法在微调与超参数搜索任务中均显著优于现有基线。
原文摘要 · Abstract (English)
Diffusion models, which iteratively denoise data samples to synthesize high-quality outputs, have achieved empirical success across domains. However, optimizing these models for downstream tasks often involves nested bilevel structures, such as tuning hyperparameters for fine-tuning tasks or noise schedules in training dynamics, where traditional bilevel methods fail due to the infinite-dimensional probability space and prohibitive sampling costs. We formalize this challenge as a generative bilevel optimization problem and address two key scenarios: (1) fine-tuning pre-trained models via an inference-only lower-level solver paired with a sample-efficient gradient estimator for the upper level, and (2) training diffusion model from scratch with noise schedule optimization by reparameterizing the lower-level problem and designing a computationally tractable gradient estimator. Our first-order bilevel framework overcomes the incompatibility of conventional bilevel methods with diffusion processes, offering theoretical grounding and computational practicality. Experiments demonstrate that our method outperforms existing fine-tuning and hyperparameter search baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。