{"ID":2858373,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.08573","arxiv_id":"2510.08573","title":"Reconstructing the local density field with combined convolutional and point cloud architecture","abstract":"We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with a point-cloud DeepSets. This combination enables efficient use of small-scale information and improves reconstruction quality relative to a U-Net-only approach. Specifically, our hybrid network recovers both clustering amplitudes and phases better than the U-Net on small scales.","short_abstract":"We construct a neural network to perform regression on the local dark-matter density field given line-of-sight peculiar velocities of dark-matter halos, biased tracers of the dark matter field. Our architecture combines a convolutional U-Net with a point-cloud DeepSets. This combination enables efficient use of small-s...","url_abs":"https://arxiv.org/abs/2510.08573","url_pdf":"https://arxiv.org/pdf/2510.08573v2","authors":"[\"Baptiste Barthe-Gold\",\"Nhat-Minh Nguyen\",\"Leander Thiele\"]","published":"2025-10-09T17:59:58Z","proceeding":"astro-ph.CO","tasks":"[\"astro-ph.CO\",\"cs.LG\",\"stat.ML\"]","methods":"[]","has_code":false}