Parameter inference of millilensed gravitational waves using neural spline flows
使用神经样条流进行毫透镜引力波的参数推断
When gravitational waves (GWs) propagate near massive objects, they undergo gravitational lensing that imprints lens model dependent modulations on the waveform. This effect provides a powerful tool for cosmological and astrophysical studies. Due to the added parameters of lenses and the uncertainty of lens models, parameter inference for lensed GW events using traditional methods is extremely time-consuming, thus requiring more efficient parameter inference methods. In this work, we explore the use of neural spline flows (NSFs) for posterior inference of blue millilensed GWs, and successfully apply NSFs to the inference of 11-dimensional lens parameters. Our results demonstrate that compared with traditional methods like Bilby DYNESTY that rely on Bayesian inference, the NSF network we built not only achieves inference accuracy comparable to traditional methods for most parameters, but also can reduce the inference time from approximately 3 days to 0.8 s on average. Additionally, the network exhibits strong generalization for the spin parameters of GW sources. It is anticipated to become a powerful tool for future low-latency searches for lensed GW signals.
展开 ▾首次将NSF用于11维毫透镜参数(含透镜质量、源参数等)的后验推断,推理时间从约3天缩短至0.8秒,并对未训练的自旋参数展现良好泛化。
引力波透镜效应的参数推断传统上依赖贝叶斯方法,但耗时巨大。近年来,归一化流等方法被用于加速参数估计,如 Green 与 Gair Green & Gair 2021 和 Dax 等 Dax+ 2021 将其应用于致密双星并合。在透镜引力波方面,Nerin 等 Nerin+ 2025 已使用条件变分自编码器进行二维快速推断。本工作将神经样条流拓展至11维完整透镜–源参数空间,推理速度较 Bilby 提升四个数量级,并展现出对自旋的泛化能力。未来可结合波光学近似和高阶模,将 NSF 作为先验压缩工具与传统方法联合使用 Williams+ 2021,从而大幅提升透镜事件的低延迟搜索能力。
预印本 2025-05-27 · 刊出 2026-05-11 · 收录 2026-10-12