R.I.P.
π»
Ghosted
Interpretable Neural Marked Statistics for Cosmological Inference
June 09, 2026 Β· Grace Period Β· π ICML 2026
Authors
Federico Semenzato, Benjamin D. Wandelt, Michele Liguori, Alvise Raccanelli
arXiv ID
2606.11295
Category
astro-ph.CO
Cross-listed
cs.LG
Citations
0
Venue
ICML 2026
Abstract
Recovering cosmological information beyond the power spectrum is a central goal for upcoming cosmological surveys, since late-time non-Gaussian signal in the matter density cannot be accessed through two-point statistics alone. Marked statistics fold part of this information back into the two-point level by reweighting the field with non-linear functions. We propose a neural marking scheme to generalize this process through a set of interpretable, physically motivated transformations that directly allow to interpret the gain in cosmological information at the morphological level. We employ a contrastive learning objective to align learnable marked summaries with the underlying cosmological parameters. At $k_{\max}=0.2\,h\mathrm{Mpc}^{-1}$, our neural mark tightens the marginalized constraint on $Ο_8$ by $2.9\times$ and on $Ξ©_m$ by $1.8\times$ compared to classical marks, breaking the $Ξ©_m-Ο_8$ degeneracy at the Fisher information level. It further reduces the parameter MSE across our cosmological parameter prior by $1.45\times$ over the best classical mark. The learned latent geometry aligns with the $Ξ©_m$ and $Ο_8$ directions in parameter space, indicating that the contrastive objective recovers the dominant axes of cosmological information. Our approach opens the door to more powerful, interpretable summary statistics for cosmological inference.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β astro-ph.CO
R.I.P.
π»
Ghosted
Learning to Predict the Cosmological Structure Formation
R.I.P.
π»
Ghosted
Estimating Cosmological Parameters from the Dark Matter Distribution
R.I.P.
π»
Ghosted
DeepCMB: Lensing Reconstruction of the Cosmic Microwave Background with Deep Neural Networks
R.I.P.
π»
Ghosted
Information theory for fields
R.I.P.
π»
Ghosted