Lorentz Model
The Lorentz model is a representation of hyperbolic geometry in which points lie on a hyperboloid and distances between points are defined by the hyperbolic metric. It offers good numerical stability and is well suited to gradient-based optimization, and is widely used in hierarchical representation learning.
Timeline (last 90 days)
Commonly used hyperbolic space models include the Poincaré disk, the upper half-plane and the Lorentz model (hyperboloid model).
The Lorentz model has relatively good numerical stability and is suitable for gradient optimization, and in recent years it has been widely used for hierarchical representation learning.
HypTI handles three kinds of information in a unified way in Lorentz hyperbolic space: clinical tabular data, MRI imaging and cross-modal interactions.
All Facts (3)
Commonly used hyperbolic space models include the Poincaré disk, the upper half-plane and the Lorentz model (hyperboloid model).
50%UnverifiedThe Lorentz model has relatively good numerical stability and is suitable for gradient optimization, and in recent years it has been widely used for hierarchical representation learning.
50%UnverifiedHypTI handles three kinds of information in a unified way in Lorentz hyperbolic space: clinical tabular data, MRI imaging and cross-modal interactions.
50%