In classical cosmological analysis of large-scale structure surveys with two-point functions, the parameter measurement precision is limited by several key degeneracies within the cosmology and astrophysics sectors. For cosmic shear, clustering amplitude ${\sigma }_8$ and matter density ${\mathrm{\Omega }}_m$ roughly follow the $S_8={\sigma }_8({\mathrm{\Omega }}_m/0.3{)}^{0.5}$ relation. In turn, $S_8$ is highly correlated with the intrinsic galaxy alignment amplitude $A_{\mathrm{IA}}$. For galaxy clustering, the bias $b_g$ is degenerate with both ${\sigma }_8$ and ${\mathrm{\Omega }}_m$, as well as the stochasticity $r_g$. Moreover, the redshift evolution of intrinsic alignment (IA) and bias can cause further parameter confusion. A tomographic two-point probe combination can partially lift these degeneracies. In this work we demonstrate that a deep-learning analysis of combined probes of weak gravitational lensing and galaxy clustering, which we call DeepLSS, can effectively break these degeneracies and yield significantly more precise constraints on ${\sigma }_8$, ${\mathrm{\Omega }}_m$, $A_{\mathrm{IA}}$, $b_g$, $r_g$, and IA redshift evolution parameter ${\eta }_{\mathrm{IA}}$. In a simulated forecast for a stage-III survey, we find that the most significant gains are in the IA sector: the precision of $A_{\mathrm{IA}}$ is increased by approximately 8 times and is almost perfectly decorrelated from $S_8$. Galaxy bias $b_g$ is improved by 1.5 times, stochasticity $r_g$ by 3 times, and the redshift evolution ${\eta }_{\mathrm{IA}}$ and ${\eta }_b$ by 1.6 times. Breaking these degeneracies leads to a significant gain in constraining power for ${\sigma }_8$ and ${\mathrm{\Omega }}_m$, with the figure of merit improved by 15 times. We give an intuitive explanation for the origin of this information gain using sensitivity maps. These results indicate that the fully numerical, map-based forward-modeling approach to cosmological inference with machine learning may play an important role in upcoming large-scale structure surveys. We discuss perspectives and challenges in its practical deployment for a full survey analysis.

中文翻译：

---

DeepLSS：通过组合探针的深度学习分析打破大规模结构中的参数退化

在具有两点函数的大规模结构调查的经典宇宙学分析中，参数测量精度受到宇宙学和天体物理学领域内几个关键退化的限制。对于宇宙剪切，聚类振幅${\sigma }_8$和物质密度${\mathrm{\Omega }}_{米}$大致按照${\mathrm{小号}}_8={\sigma }_8({\mathrm{\Omega }}_{米}/0.3{)}^{0.5}$关系。反过来，${\mathrm{小号}}_8$与固有星系对齐幅度高度相关${\mathrm{一个}}_{\mathrm{IA}}$. 对于星系聚类，偏差$b_G$两者都退化${\sigma }_8$和${\mathrm{\Omega }}_{米}$，以及随机性$r_G$. 此外，内在对齐 (IA) 和偏差的红移演变会导致进一步的参数混淆。断层扫描两点探针组合可以部分解除这些退化。在这项工作中，我们证明了对弱引力透镜和星系聚类组合探测器的深度学习分析，我们称之为 DeepLSS，可以有效地打破这些简并并产生更精确的约束${\sigma }_8$,${\mathrm{\Omega }}_{米}$,${\mathrm{一个}}_{\mathrm{IA}}$,$b_G$,$r_G$, 和 IA 红移演化参数${\eta }_{\mathrm{IA}}$. 在第三阶段调查的模拟预测中，我们发现最显着的收益出现在 IA 部门：${\mathrm{一个}}_{\mathrm{IA}}$增加了大约 8 倍，并且几乎完全从${\mathrm{小号}}_8$. 星系偏差$b_G$提高了1.5倍，随机性$r_G$3倍，红移演化${\eta }_{\mathrm{IA}}$和${\eta }_b$1.6 倍。打破这些退化可以显着提高约束力${\sigma }_8$和${\mathrm{\Omega }}_{米}$，品质因数提高了 15 倍。我们使用敏感度图对这种信息增益的来源进行了直观的解释。这些结果表明，使用机器学习进行宇宙学推断的全数值、基于地图的前向建模方法可能在即将进行的大规模结构调查中发挥重要作用。我们讨论了其实际部署中的观点和挑战，以进行全面的调查分析。