Set-based Implicit Likelihood Inference of Galaxy Cluster Mass
Not on the map. Why?
Abstract (arXiv)
We present a set-based machine learning framework that infers posterior distributions of galaxy cluster masses from projected galaxy dynamics. Our model combines Deep Sets and conditional normalizing flows to incorporate both positional and velocity information of member galaxies to predict residual corrections to the M-σ relation for improved interpretability. Trained on the Uchuu-UniverseMachine simulation, our approach significantly reduces scatter and provides well-calibrated uncertainties across the full mass range compared to traditional dynamical estimates.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 12 of its 39 references that are in the map. First posted on arXiv 27 Jul 2025.
Builds on
12 of 39 references.
References · 12
- 2019Neural Spline Flowscited by 596
- 2019The frontier of simulation-based inferencecited by 502
- 2018Pyro: Deep Universal Probabilistic Programmingcited by 380
- 2019Automatic Posterior Transformation for Likelihood-Free Inferencecited by 219
- 2017Flexible statistical inference for mechanistic models of neural dynamicscited by 163
- 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inferencecited by 46
- 2020Invertible Generative Modeling using Linear Rational Splinescited by 40
- 2023Robust Field-level Likelihood-free Inference with Galaxiescited by 11
- 2020Mass Estimation of Galaxy Clusters with Deep Learning I: Sunyaev-Zel'dovich Effectcited by 6
- 2022Predicting the Thermal Sunyaev-Zel'dovich Field using Modular and Equivariant Set-Based Neural Networkscited by 6
- 2020Mass Estimation of Galaxy Clusters with Deep Learning II: CMB Cluster Lensingcited by 4
- 2024Estimating Dark Matter Halo Masses in Simulated Galaxy Clusters with Graph Neural Networkscited by 1
Built on by
Not cited yet.