AI RESEARCH
Richer Bayesian Last Layers with Subsampled NTK Features
arXiv CS.LG
•
ArXi:2602.01279v2 Announce Type: replace Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty because they apply a Bayesian treatment only to the final layer, ignoring uncertainty induced by earlier layers. We propose a method that improves BLLs by leveraging a projection of Neural Tangent Kernel (NTK) features onto the space spanned by the last-layer features.