Bayesian Cosmic Void Finding with Graph Flows

• URL: http://arxiv.org/abs/2602.14630v1
• Date: Mon, 16 Feb 2026 10:37:53 GMT
• Title: Bayesian Cosmic Void Finding with Graph Flows
• Abstract summary: Finding genuine matter underdensities in sparse galaxy surveys is an under-constrained problem.<n>Traditional void finding algorithms produce deterministic void catalogs, neglecting the nature of the problem.<n>We present a method to sample from the mapping from galaxy catalogs to arbitrary void definitions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cosmic voids contain higher-order cosmological information and are of interest for astroparticle physics. Finding genuine matter underdensities in sparse galaxy surveys is, however, an underconstrained problem. Traditional void finding algorithms produce deterministic void catalogs, neglecting the probabilistic nature of the problem. We present a method to sample from the stochastic mapping from galaxy catalogs to arbitrary void definitions. Our algorithm uses a deep graph neural network to evolve "test particles" according to a flow-matching objective. We demonstrate the method in a simplified example setting but outline steps to generalize it towards practically usable void finders. Trained on a deterministic teacher, the model performs well but has considerable stochasticity which we interpret as regularization. Cosmological information in the predicted void catalogs outperforms the teacher. On the one hand, our method can cheaply emulate existing void finders with apparently useful regularization. More importantly, it also allows us to find the Bayes-optimal mapping between observed galaxies and any void definition. This includes definitions operating at the level of simulated matter density and velocity fields.

Related papers

• What AstroPT knows about galaxies, and what that can teach us about LLMs [2.4906335493319207]
  Interpretability research increasingly asks when concepts emerge during training and whether linear probes recover real structure.<n>We propose the use of astronomical ground truth through AstroPT, a transformer trained on millions of galaxy images.
  arXiv  Detail & Related papers  (2026-08-23T21:40:26Z)
• Learn to Rank: Visual Attribution by Learning Importance Ranking [58.69028273772474]
  We propose a new approach to generate visual attribution maps for computer vision models.<n>Our method produces dense, pixel-level attributions in a single forward pass with optional, few-step gradient refinement.<n>Our experiments demonstrate consistent quantitative improvements and sharper, boundary-aligned explanations.
  arXiv  Detail & Related papers  (2026-04-07T12:53:22Z)
• (Exhaustive) Symbolic Regression and model selection by minimum description length [0.0]
  Symbolic regression is the machine learning method for learning functions from data.<n>Traditional algorithms have an unknown (and likely significant) probability of failing to find any given good function.<n>I propose an exhaustive search and model selection by the minimum description length principle.
  arXiv  Detail & Related papers  (2025-07-17T12:04:15Z)
• Learning the Universe: Learning to Optimize Cosmic Initial Conditions with Non-Differentiable Structure Formation Models [0.22940141855172033]
  We introduce Learning the Universe by Learning to Optimize (LULO) for reconstructing the 3D cosmic initial conditions.<n>LULO is a gradient-free framework for reconstructing the 3D cosmic initial conditions.<n>We demonstrate the method by accurately reconstructing initial conditions from $M_200mathrmc$ halos identified in a dark matter-only $N$-body simulation.
  arXiv  Detail & Related papers  (2025-02-18T19:17:01Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Accelerating Black-Box Molecular Property Optimization by Adaptively Learning Sparse Subspaces [0.0]
  We show that our proposed method substantially outperforms existing MPO methods on a variety of benchmark and real-world problems. Specifically, we show that our method can routinely find near-optimal molecules out of a set of more than $>100$k alternatives within 100 or fewer expensive queries.
  arXiv  Detail & Related papers  (2024-01-02T18:34:29Z)
• Cosmology from Galaxy Redshift Surveys with PointNet [65.89809800010927]
  In cosmology, galaxy redshift surveys resemble such a permutation invariant collection of positions in space. We employ a textitPointNet-like neural network to regress the values of the cosmological parameters directly from point cloud data. Our implementation of PointNets can analyse inputs of $mathcalO(104) - mathcalO(105)$ galaxies at a time, which improves upon earlier work for this application by roughly two orders of magnitude.
  arXiv  Detail & Related papers  (2022-11-22T15:35:05Z)
• Semi-Supervised Domain Adaptation for Cross-Survey Galaxy Morphology Classification and Anomaly Detection [57.85347204640585]
  We develop a Universal Domain Adaptation method DeepAstroUDA. It can be applied to datasets with different types of class overlap. For the first time, we demonstrate the successful use of domain adaptation on two very different observational datasets.
  arXiv  Detail & Related papers  (2022-11-01T18:07:21Z)
• Understanding of the properties of neural network approaches for transient light curve approximations [37.91290708320157]
  This paper presents a search for the best-performing methods to approximate the observed light curves over time and wavelength. Test datasets include simulated PLAsTiCC and real Zwicky Transient Facility Bright Transient Survey light curves of transients.
  arXiv  Detail & Related papers  (2022-09-15T18:00:08Z)
• Inferring Structural Parameters of Low-Surface-Brightness-Galaxies with Uncertainty Quantification using Bayesian Neural Networks [70.80563014913676]
  We show that a Bayesian Neural Network (BNN) can be used for the inference, with uncertainty, of such parameters from simulated low-surface-brightness galaxy images. Compared to traditional profile-fitting methods, we show that the uncertainties obtained using BNNs are comparable in magnitude, well-calibrated, and the point estimates of the parameters are closer to the true values.
  arXiv  Detail & Related papers  (2022-07-07T17:55:26Z)
• Sensitivity Estimation for Dark Matter Subhalos in Synthetic Gaia DR2 using Deep Learning [0.0]
  We describe the challenges of detecting stars whose phase-space distribution may be perturbed by the passage of dark matter subhalos using a machine learning approach. We first quantify the magnitude of the perturbations in the simulated galaxies using an anomaly detection algorithm. We find that a classification algorithm optimized on about half a billion synthetic star observables exhibits mild but nonzero sensitivity.
  arXiv  Detail & Related papers  (2022-03-15T18:00:02Z)
• On the Benefits of Large Learning Rates for Kernel Methods [110.03020563291788]
  We show that a phenomenon can be precisely characterized in the context of kernel methods. We consider the minimization of a quadratic objective in a separable Hilbert space, and show that with early stopping, the choice of learning rate influences the spectral decomposition of the obtained solution.
  arXiv  Detail & Related papers  (2022-02-28T13:01:04Z)
• Latent World Models For Intrinsically Motivated Exploration [140.21871701134626]
  We present a self-supervised representation learning method for image-based observations. We consider episodic and life-long uncertainties to guide the exploration of partially observable environments.
  arXiv  Detail & Related papers  (2020-10-05T19:47:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.