Showing 2026Show all
2 papers · 1 filter
cs.LG2026
Contrastive Linearized Laplace: Loss Geometry, Valid Repairs, and Reliable Cores
Francisco J. Sáez-Maldonado, Luis A. Ortega, Andrés R. Masegosa +1
While contrastive learning is widely used to learn deterministic representations, it does not inherently provide estimates of uncertainty. Post-hoc uncertainty estimation methods,…
cs.LG2026
An Analysis of Posterior Collapse, Parameterization and Initialization in Variational Deep Gaussian Processes
Francisco Javier Sáez-Maldonado, Juan Maroñas, Daniel Hernández-Lobato
DGPs are probabilistic models with remarkable prediction performance that concatenate GPs across several layers. Exact inference in DGPs is intractable, and variational inference i…