Para-CFlows: C k-universal Diffeomorphism Approximators as Superior Neural Surrogates
–Neural Information Processing Systems
Therefore, beyond the distributional universality, it is also important to investigate the universality from the mapping perspective. As INNs are always invertible, it is natural to consider their approximation ability to diffeomorphisms.
Neural Information Processing Systems
Aug-18-2025, 05:28:12 GMT
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Representation & Reasoning (1.00)
- Vision (0.68)
- Information Technology > Artificial Intelligence