arXiv stat.ML
· Papers
Optimality of Sub-network Laplace Approximations: New Results and Methods
arXiv:2605.09075v2 Announce Type: replace Abstract: Although the Laplace approximation offers a simple route to uncertainty quantification in deep neural networks, its reliance on inverting large Hessian matrices has motivated a range of computationally feasible low-dimensional or sparse approximations. A prominent cla