arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14040stat.MLcs.LG
收藏

一种实用的采样扩散路径

A Practical Diffusion Path for Sampling

ENSAE(法国国立统计与经济管理学校);CREST(CREST(法国统计与经济研究中心));IP Paris(巴黎理工学院)

Omar Chehab, Anna Korba

AI总结:

针对无目标分布样本时扩散模型得分估计困难的问题,提出基于膨胀路径的闭式得分向量计算方法及自适应步长朗之万动力学实现,在多任务上性能优于经典方法。

摘要:

当目标概率分布的样本可获取且能被高效采样时,扩散模型是生成建模领域的最优方法,它利用得分匹配估计引导朗之万过程的得分向量。然而,在无法获取目标分布样本的场景下——例如目标分布的密度仅已知到差一个归一化常数的程度时——得分估计任务极具挑战性。以往的方法依赖蒙特卡洛估计器,这类方法要么实现计算量极大,要么样本效率低下。在本研究中,我们提出了一种计算上更具吸引力的替代方案,该方案基于所谓的dilation path(膨胀路径),能够得到闭式表达的得分向量。该路径通过卷积在狄拉克分布与目标分布之间进行插值。我们提出了一种由膨胀路径引导的、采用自适应步长的朗之万动力学的简单实现方式。我们在一系列任务上验证了该采样方法的效果,结果表明其性能优于经典的替代方法。

英文摘要:

Diffusion models are state-of-the-art methods in generative modeling when samples from a target probability distribution are available, and can be efficiently sampled, using score matching to estimate score vectors guiding a Langevin process. However, in the setting where samples from the target are not available, e.g. when this target's density is known up to a normalization constant, the score estimation task is challenging. Previous approaches rely on Monte Carlo estimators that are either computationally heavy to implement or sample-inefficient. In this work, we propose a computationally attractive alternative, relying on the so-called dilation path, that yields score vectors that are available in closed-form. This path interpolates between a Dirac and the target distribution using a convolution. We propose a simple implementation of Langevin dynamics guided by the dilation path, using adaptive step-sizes. We illustrate the results of our sampling method on a range of tasks, and shows it performs better than classical alternatives.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑