AI RESEARCH
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
arXiv CS.LG
•
ArXi:2605.26900v1 Announce Type: new A fundamental open question in self-supervised learning (SSL) is the explicit characterization of the optimal geometry of the learned representations. Recently, LeJEPA identified isotropic Gaussian embeddings as optimal for minimizing downstream prediction risk in Euclidean spaces. However, the corresponding problem for distributions ed on lower-dimensional manifolds, such as the hypersphere, remains unexplored.