AI RESEARCH

Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

arXiv CS.AI

ArXi:2605.20107v1 Announce Type: cross JEPAs often regularize one-view embeddings toward an isotropic Gaussian, implicitly baking Euclidean symmetry into the representation. We show that this is not merely a benign default. For a known structured downstream geometry $H\succ0$, the minimax and maximum-entropy covariance under a Hamiltonian energy budget is $(c/d)H^{-1}$, and Euclidean isotropy incurs a closed-form price of isotropy.