arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.04763stat.MLcs.LG
收藏

关于使用近似传输映射的采样

On Sampling with Approximate Transport Maps

École Polytechnique(巴黎综合理工学院)

Louis Grenioux, Alain Durmus, Éric Moulines, Marylou Gabrié

AI总结:

本研究首次对比了基于流提议和流重参数化的 NF 增强采样方法,发现前者更适用于中高维多模态目标,后者在高维和训练不足时更稳健,并推导了新混合时间定量界限。

摘要:

传输映射通过将具有复杂几何结构的分布转化为更易处理的分布,能够简化对其的采样。随着 Normalizing Flows (NF) 的发展,这种方法的潜力日益凸显。NF 是用深度神经网络参数化的映射,经过训练可将参考分布推向目标分布。近期提出的 NF 增强采样器将(马尔可夫链)蒙特卡罗方法与以下两者之一相融合:(i) 从流中提取提议样本,或 (ii) 基于流的重新参数化。在这两种情况下,学习到的传输映射的质量均决定了性能表现。本研究首次阐明了这两种方法的相对优缺点。我们的研究结论是,对于多模态目标,使用基于流的提议可以可靠地进行处理,直至中等偏高的维度。相比之下,依赖重新参数化的方法在处理多模态时存在困难,但在高维设置和训练不足的情况下则更为稳健。为了进一步说明目标与提议之间适配度的影响,我们还为 Independent Metropolis-Hastings 采样器的混合时间推导出了一个新的定量界限。

英文摘要:

Transport maps can ease the sampling of distributions with non-trivial geometries by transforming them into distributions that are easier to handle. The potential of this approach has risen with the development of Normalizing Flows (NF) which are maps parameterized with deep neural networks trained to push a reference distribution towards a target. NF-enhanced samplers recently proposed blend (Markov chain) Monte Carlo methods with either (i) proposal draws from the flow or (ii) a flow-based reparametrization. In both cases, the quality of the learned transport conditions performance. The present work clarifies for the first time the relative strengths and weaknesses of these two approaches. Our study concludes that multimodal targets can be reliably handled with flow-based proposals up to moderately high dimensions. In contrast, methods relying on reparametrization struggle with multimodality but are more robust otherwise in high-dimensional settings and under poor training. To further illustrate the influence of target-proposal adequacy, we also derive a new quantitative bound for the mixing time of the Independent Metropolis-Hastings sampler.

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。

↑