Global Trend Radar
arXiv cs.LG (Machine Learning) INT ai 2026-05-08 13:00

Covering-Space Normalizing Flows: Approximating Pushforwards on Lens Spaces

元記事を開く →

分析結果

カテゴリ
宇宙
重要度
53
トレンドスコア
12
要約
arXiv:2511.22882v2 Announce Type: replace Abstract: We construct pushforward distributions via the universal covering map rho: S^3 -> L(p;q) with the goal of approximating these distributions using flows on L(p;q). We hi
キーワード
arXiv:2511.22882v2 Announce Type: replace Abstract: We construct pushforward distributions via the universal covering map rho: S^3 -> L(p;q) with the goal of approximating these distributions using flows on L(p;q). We highlight that our method deletes redundancies in the case of a symmetric S^3 distribution. Using our model, we approximate the pushforwards of von Mises-Fisher-induced target densities as well as that of a Z_12-symmetric Boltzmann distribution on S^3 constructed to model benzene. arXiv:2511.22882v2 Announce Type: replace Abstract: We construct pushforward distributions via the universal covering map rho: S^3 -> L(p;q) with the goal of approximating these distributions using flows on L(p;q). We highlight that our method deletes redundancies in the case of a symmetric S^3 distribution. Using our model, we approximate the pushforwards of von Mises-Fisher-induced target densities as well as that of a Z_12-symmetric Boltzmann distribution on S^3 constructed to model benzene.