2026
Richer Bayesian Last Layers with Subsampled NTK Features
Sergio Calvo Ordoñez, Jonathan Plenk, Richard Bergna, Alvaro Cartea, Yarin Gal, Jose Miguel Hernandez-Lobato +1
ICML 2026poster
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…