论文标题
强大的神经网络增强局部原始非高斯性估计
Robust Neural Network-Enhanced Estimation of Local Primordial Non-Gaussianity
论文作者
论文摘要
当应用于宇宙的非线性物质分布时，神经网络已被证明是宇宙学参数的非常统计敏感的探针，例如线性扰动振幅$σ_8$。但是，当用作“黑匣子”时，神经网络对男性不确定性并不强大。我们通过训练神经网络来局部估计$σ_8$，并将这些本地估计值与大规模密度字段相关联，我们提出了一个强大的体系结构，用于约束原始非高斯$ f_ {nl} $。我们将方法应用于n体模拟，并表明$σ（f_ {nl}）$是从基于标准的晕圈方法获得的约束优点3.5倍。我们表明，我们的方法具有与大规模光环偏置相同的鲁棒性属性：Baryonic物理可以更改估计的$ f_ {nl} $的归一化，但是无法更改是否检测到$ f_ {nl} $。
When applied to the non-linear matter distribution of the universe, neural networks have been shown to be very statistically sensitive probes of cosmological parameters, such as the linear perturbation amplitude $σ_8$. However, when used as a "black box", neural networks are not robust to baryonic uncertainty. We propose a robust architecture for constraining primordial non-Gaussianity $f_{NL}$, by training a neural network to locally estimate $σ_8$, and correlating these local estimates with the large-scale density field. We apply our method to N-body simulations, and show that $σ(f_{NL})$ is 3.5 times better than the constraint obtained from a standard halo-based approach. We show that our method has the same robustness property as large-scale halo bias: baryonic physics can change the normalization of the estimated $f_{NL}$, but cannot change whether $f_{NL}$ is detected.
