Weak Lensing (WL) surveys are reaching unprecedented depths, enabling the investigation of very small angular scales. At these scales, nonlinear gravitational effects lead to higher-order correlations making the matter distribution highly non-Gaussian. Extracting this information using traditional statistics has proven difficult, and Machine Learning based summary statistics have emerged as a powerful alternative. We explore the capabilities of a discriminative, Convolutional Neural Networks (CNN) based approach, focusing on parameter constraints in the (Ω _m , σ₈) cosmological parameter space. Leveraging novel training loss functions and network representations on WL mock datasets without baryons, we show that our models achieve ~ 5 times higher figure of merit in the σ_8-Ω _m plane than the power spectrum, ~ 3 times higher than peak counts, and ~ 2 times higher than previous CNN-learned summary statistics and scattering transforms, for noise levels relevant to Rubin or Euclid. For WL convergence maps with baryonic physics, our models achieve ~ 2.3 times stronger constraining power than the power spectrum at these noise levels, also outperforming previous summary statistics. To further explore the possibilities of CNNs for this task, we also discuss transfer learning where we adapt pre-trained models, trained on different tasks or datasets, for cosmological inference, finding that these do not improve the performance.

中文翻译：

---

使用卷积神经网络对弱透镜的宇宙学约束进行比较研究


弱透镜（WL）调查正在达到前所未有的深度，使得能够对非常小的角度尺度进行调查。在这些尺度上，非线性引力效应会导致高阶相关性，从而使物质分布高度非高斯分布。事实证明，使用传统统计数据提取这些信息很困难，而基于机器学习的摘要统计数据已成为一种强大的替代方案。我们探索基于判别式卷积神经网络 (CNN) 的方法的功能，重点关注 (Ω_米, σ ₈ ) 宇宙学参数空间。利用新颖的训练损失函数和没有重子的 WL 模拟数据集上的网络表示，我们表明我们的模型在 σ _8- Ω 中实现了大约 5 倍的品质因数_米对于与 Rubin 或 Euclid 相关的噪声水平，平面比功率谱高，比峰值计数高约 3 倍，比之前 CNN 学习的汇总统计和散射变换高约 2 倍。对于具有重子物理的 WL 收敛图，我们的模型在这些噪声水平下实现了比功率谱强约 2.3 倍的约束能力，也优于之前的汇总统计数据。为了进一步探索 CNN 完成此任务的可能性，我们还讨论了迁移学习，其中我们采用预先训练的模型，在不同的任务或数据集上进行训练，以进行宇宙学推理，但发现这些并不能提高性能。