Neural Isometries: Taming Transformations for Equivariant ML
–Neural Information Processing Systems
Specifically, we regularize the latent space such that maps between encodings preserve a learned inner product and commute with a learned functional operator, in the same manner as rigid-body transformations commute with the Laplacian.
Neural Information Processing Systems
Oct-9-2025, 18:29:53 GMT
- Country:
- Asia (0.14)
- North America > United States (0.68)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Government > Regional Government (0.46)
- Information Technology (0.46)
- Technology:
- Information Technology > Artificial Intelligence
- Machine Learning > Neural Networks (1.00)
- Representation & Reasoning (1.00)
- Vision (1.00)
- Information Technology > Artificial Intelligence