activity
20242026
collaborators

7 papers

cs.LG2026

Uncertainty Estimation and Generalization Bounds for Modern Deep Learning

Luis A. Ortega

This thesis investigates how Bayesian principles can deepen our understanding of modern deep learning systems. While neural networks achieve remarkable predictive performance, thei…

cs.LG2026

Flow-Transformed Implicit Processes for Function-Space Variational Inference

Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen

Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performin…

cs.LG2026

Fixed-Mean Gaussian Processes for Post-hoc Bayesian Deep Learning

Luis A. Ortega, Simón Rodríguez-Santana, Daniel Hernández-Lobato

Recently, there has been an increasing interest in performing post-hoc uncertainty estimation about the predictions of pre-trained deep neural networks (DNNs). Given a pre-trained…

stat.ML2026

Improving the Linearized Laplace Approximation via Quadratic Approximations

Pedro Jiménez, Luis A. Ortega, Pablo Morales-Álvarez +1

Deep neural networks (DNNs) often produce overconfident out-of-distribution predictions, motivating Bayesian uncertainty quantification. The Linearized Laplace Approximation (LLA)…

cs.LG2026

Scalable Linearized Laplace Approximation via Surrogate Neural Kernel

Luis A. Ortega, Simón Rodríguez-Santana, Daniel Hernández-Lobato

We introduce a scalable method to approximate the kernel of the Linearized Laplace Approximation (LLA). For this, we use a surrogate deep neural network (DNN) that learns a compact…

cs.LG2025

PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime

Andrés R. Masegosa, Luis A. Ortega

This paper introduces a distribution-dependent PAC-Chernoff bound that exhibits perfect tightness for interpolators, even within over-parameterized model classes. This bound, which…