Paper on covering-space normalizing flows withdrawn by author

This paper, "Covering-Space Normalizing Flows: Approximating Pushforwards on Lens Spaces," introduces a method for constructing pushforward distributions using a universal covering map. The approach aims to approximate these distributions with flows on lens spaces, offering benefits such as deleting redundancies for symmetric distributions. The authors demonstrate its application by approximating pushforwards of von Mises-Fisher-induced target densities and a Z_12-symmetric Boltzmann distribution modeling benzene. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a new mathematical framework for approximating complex distributions, potentially aiding in generative modeling and data analysis.

RANK_REASON This is a research paper published on arXiv detailing a novel methodology in machine learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• William Ghanem
• S^3
• L(p;q)
• Z_12
• benzene

• paper