נופים קהלריים לירידות רשתות עם תואר כולל חיפוש והשמדה של המניפולד הקלאבי-יו

תקציר מקורי באנגליתarXiv:2608.19584v3 Announce Type: replace Abstract: We study landscapes for complex-parameterized networks. Our approach is motivated with an information-theoretic manifold perspective of the parameter and via classical optimization guarantees although of complex geometric variety such as through Dolbeault asymptotics. The descent path admits a K\"ahler information metric under a cross-entropy via the Wirtinger Hessian on the log-likelihood potential. We restrict attention to a descent update rule with natural gradient descent via a differentiated loss scaled by the inverse metric, so the descent path remains in the holomorphic tangent bundle. We emphasize Calabi-Yau information manifolds which profane theoretical guarantees via an ill-curvature-conditioned landscape. We focus on Calabi-Ya