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 2610.02448astro-ph.IMastro-ph.HEgr-qc

学习近似等距嵌入以实现高效模板放置

Learning Approximate Isometric Embeddings for Efficient Template Placement

Alexandra Wernersson, Jessica Irwin, Melissa Lopez, Sarah Caudill

首次发表
浏览论文内容

中文总结 AI 辅助

本文提出 isobank,一种归一化流学习近似等距嵌入,在引力波模板放置中,以更少模板实现高覆盖率,提高效率。

中文摘要 AI 辅助

球覆盖问题在科学中具有广泛的应用,然而,在弯曲的高维流形上,精确解在计算上是不可行的,因为距离必须使用依赖于位置的度量来评估。我们提出了 isobank,一种归一化流,它学习一个近似等距的坐标变换,使得潜在空间中的欧几里得距离近似物理参数空间中由度量引起的固有距离。这使得在潜在空间中使用欧几里得距离检查进行模板放置成为可能,从而避免在放置过程中重复进行度量评估。我们在引力波模板库构建的背景下评估 isobank,其中球覆盖问题对应于模板放置问题。在五维偏心双星参数空间中,isobank 在最大失配为 μ=0.03 时达到 97% 的覆盖率,比最先进的随机放置代码 mbank(达到 94% 的覆盖率)少使用 23% 的模板。覆盖率是在均匀分布在质量、自旋和偏心率上的独立注入上测量的,使用精确的波形匹配而非度量近似。训练该流大约需要 2.5 小时,在 32 个 CPU 核心上放置库不到 1 小时。isobank 在 Github 上公开可用,网址为 https URL。

英文摘要

The sphere covering problem has broad applications in science however, exact solutions are computationally infeasible on curved, high-dimensional manifolds because distances must be evaluated using a position-dependent metric. We present $\texttt{isobank}$, a normalizing flow that learns an approximately isometric coordinate transformation, such that Euclidean distances in the latent space approximate metric-induced proper distances in the physical parameter space. This enables template placement using Euclidean distance checks in the latent space, avoiding repeated metric evaluations during placement. We evaluate $\texttt{isobank}$ in the context of gravitational wave template bank construction, where the sphere covering problem corresponds to the template placement problem. On a five-dimensional eccentric binary parameter space, $\texttt{isobank}$ reaches 97\% coverage at a maximum mismatch of $μ=0.03$ with 23\% fewer templates than the state-of-the-art stochastic placement code $\texttt{mbank}$, which reaches 94\% coverage. Coverage is measured on independent injections drawn uniformly over the masses, spins and eccentricity, using the exact waveform match rather than the metric approximation. Training the flow takes about 2.5h and placing the bank under 1h on 32 CPU cores. $\texttt{isobank}$ is publicly available on Github https://github.com/Alexandra-Wernersson/isobank

发表机构

  • Nikhef, National Institute for Nuclear Physics and High-Energy Physics(荷兰国家核物理与高能物理研究所)
  • CAISR Health, Halmstad University(哈尔姆斯塔德大学)
  • Institute for Gravitational and Subatomic Physics (GRASP), Utrecht University(乌得勒支大学引力与亚原子物理研究所)
  • University of Massachusetts Dartmouth(马萨诸塞大学达特茅斯分校)

机构由 AI 辅助整理,请以论文原文为准。

补充信息

↑