Accelerating Bayesian sampling for massive black hole binaries with prior constraints from conditional variational autoencoder
利用条件变分自编码器先验约束加速大质量黑洞双星的贝叶斯采样
A conditional variational autoencoder (CVAE) model is employed for parameter inference on gravitational waves (GW) signals of massive black hole binaries, considering joint observations with a network of three space-based GW detectors. Our experiments show that the trained CVAE model can estimate the posterior distribution of source parameters in approximately one second, while the standard Bayesian sampling method, utilizing parallel computation across 16 CPU cores, takes an average of 20 hours for a GW signal instance. However, the sampling distributions from CVAE exhibit lighter tails, appearing broader when compared to the standard Bayesian sampling results. By using CVAE results to constrain the prior range for Bayesian sampling, the sampling time is reduced by a factor of <inline-formula><mml:math><mml:mrow><mml:mo>~</mml:mo><mml:mn>6</mml:mn></mml:mrow></mml:math></inline-formula> while maintaining the similar precision of the Bayesian results.
展开 ▾首次将CVAE应用于大质量黑洞双星参数推断,并提出只利用CVAE输出的边界信息作为先验约束,巧妙地解决了深度学习后验过宽的问题,实现了廉价快速估计与高精度贝叶斯采样的有效结合。
传统贝叶斯嵌套采样计算代价高昂。近年来深度学习方法如CVAE和归一化流已用于基态黑洞双星的快速参数估计(Gabbard+ 2022、Green+ 2021),但直接用于大质量黑洞双星(MBHB)时,其后验分布往往过宽(Du+ 2024)。受EMRI分级参数空间缩减工作的启发(Ye+ 2024),本文不再追求直接拟合后验形状,转而提取CVAE预测分布的边界信息作为约束性先验,从而大幅加速贝叶斯采样。未来该方法可推广到其他高信噪比引力波源,并可与其他加速技巧(如相对分箱、多频带等)结合,进一步提升参数估计效率。
预印本 2025-02-13 · 刊出 2025-05-30 · 收录 2026-10-14