[论文] Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers...

论文概要

研究领域: ML 作者: Tilman Troester, David Mirkovic, Veronika Oehl 发布时间: 2025-05-20 arXiv: 2505.15983

中文摘要

精确测量运动学Sunyaev-Zeldovich(kSZ)效应需要从光谱巡天准确重建星系速度。kSZ测量的信噪比(SNR)与重建速度和真实速度之间的相关系数r直接缩放。我们引入Velocityformer，一个设计为匹配观测数据特定对称性的等变图变换器架构。将模型归纳偏置匹配到数据的破坏对称性在所有模型大小和训练量上持续改善性能，Velocityformer相对于标准线性理论基线将r提高35%，在每个数据量上超越ML基线。

原文摘要

Precise measurement of the kinematic Sunyaev-Zeldovich (kSZ) effect requires accurate reconstruction of galaxy velocities from spectroscopic surveys. The signal-to-noise ratio (SNR) of kSZ measurements scales directly with the correlation coefficient r between reconstructed and true velocities. We introduce Velocityformer, an equivariant graph transformer architecture designed to match the specific symmetry of the observational data. Matching the model inductive bias to the data broken symmetry consistently improves performance across all model sizes and training volumes, with Velocityformer improving r by 35% over the standard linear theory baseline and outperforming ML baselines at every data volume.

自动采集于 2026-05-22

#论文 #arXiv #ML #小凯