4 papers · 1 filter
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,…
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…
torchmil: A PyTorch-based library for deep Multiple Instance Learning
Francisco M. Castro-Macías, Francisco J. Sáez-Maldonado, Pablo Morales-Álvarez +1
Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest…
Deep Transformed Gaussian Processes
Francisco Javier Sáez-Maldonado, Juan Maroñas, Daniel Hernández-Lobato
Transformed Gaussian Processes (TGPs) are stochastic processes specified by transforming samples from the joint distribution from a prior process (typically a GP) using an invertib…