Topological Obstructions and How to A void Them
–Neural Information Processing Systems
In this paper, we theoretically and empirically characterize obstructions to training encoders with geometric latent spaces. We show that local optima can arise due to singularities (e.g.
Neural Information Processing Systems
Feb-8-2026, 13:56:05 GMT
- Country:
- North America
- United States > California
- Monterey County > Monterey (0.04)
- Canada > Alberta
- United States > California
- Europe > Netherlands
- North Holland > Amsterdam (0.04)
- North Brabant > Eindhoven (0.04)
- Asia > China
- Guangxi Province > Nanning (0.04)
- North America
- Genre:
- Research Report (0.46)
- Industry:
- Health & Medicine (0.46)
- Technology: