# DeepLSS: breaking parameter degeneracies in large scale structure with deep learning analysis of combined probes

arXiv: https://arxiv.org/abs/2203.09616 · HTML: https://mlsanity.com/paper/2203.09616/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 64 references that are in the map.
- First posted on arXiv 17 Mar 2022.

## Builds on (most cited first, 7 of 7)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Depthwise Separable Convolutions for Neural Machine Translation](https://mlsanity.com/paper/1706.03059/) (2017)
- [Gaussian Process Conditional Density Estimation](https://mlsanity.com/paper/1810.12750/) (2018)
- [AutoClip: Adaptive Gradient Clipping for Source Separation Networks](https://mlsanity.com/paper/2007.14469/) (2020)
- [Massive data compression for parameter-dependent covariance matrices](https://mlsanity.com/paper/1707.06529/) (2017)

## Built on by (most cited first, 5 of 5)

- [Explaining dark matter halo density profiles with neural networks](https://mlsanity.com/paper/2305.03077/) (2023)
- [Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects](https://mlsanity.com/paper/2310.15234/) (2023)
- [Interpreting "Interpretability" and Explaining "Explainability" in Machine Learning in Physics](https://mlsanity.com/paper/2606.26228/) (2026)
- [Achieving Occam's Razor: Deep Learning for Optimal Model Reduction](https://mlsanity.com/paper/2303.13746/) (2023)
- [Dark Energy Survey Year 3 results: Simulation-based wCDM inference from weak lensing and galaxy clustering maps with deep learning: Analysis design](https://mlsanity.com/paper/2511.04681/) (2025)

## Abstract (arXiv)

In classical cosmological analysis of large scale structure surveys with 2-pt functions, the parameter measurement precision is limited by several key degeneracies within the cosmology and astrophysics sectors. For cosmic shear, clustering amplitude σ8 and matter density Omegam roughly follow the S8=σ8(Omegam/0.3)0.5 relation. In turn, S8 is highly correlated with the intrinsic galaxy alignment amplitude A_rmIA. For galaxy clustering, the bias bg is degenerate with both σ8 and Omegam, as well as the stochasticity rg. Moreover, the redshift evolution of IA and bias can cause further parameter confusion. A tomographic 2-pt 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 σ8, Omegam, A_rmIA, bg, rg, and IA redshift evolution parameter η_rmIA. The most significant gains are in the IA sector: the precision of A_rmIA is increased by approximately 8x and is almost perfectly decorrelated from S8. Galaxy bias bg is improved by 1.5x, stochasticity rg by 3x, and the redshift evolution η_rmIA and ηb by 1.6x. Breaking these degeneracies leads to a significant gain in constraining power for σ8 and Omegam, with the figure of merit improved by 15x. 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 LSS surveys. We discuss perspectives and challenges in its practical deployment for a full survey analysis.