4 citations · 7 across the 11 of their papers we have counts for
13 papers
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,…
Generalized Matheron Variational Implicit Processes
Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen
Implicit-process priors specify distributions over functions through sample-forward mechanisms such as Bayesian neural networks and stochastic simulators, but their function-space…
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…
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…
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)…
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…
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…
PAC-Bayes-Chernoff bounds for unbounded losses
Ioar Casado, Luis A. Ortega, Aritz Pérez +1
We introduce a new PAC-Bayes oracle bound for unbounded losses that extends Cramér-Chernoff bounds to the PAC-Bayesian setting. The proof technique relies on controlling the tails…
If there is no underfitting, there is no Cold Posterior Effect
Yijie Zhang, Yi-Shan Wu, Luis A. Ortega +1
The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature , the resulting posterior predictive could have b…
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…
Variational Linearized Laplace Approximation for Bayesian Deep Learning
Luis A. Ortega, Simón Rodríguez Santana, Daniel Hernández-Lobato
The Linearized Laplace Approximation (LLA) has been recently used to perform uncertainty estimation on the predictions of pre-trained deep neural networks (DNNs). However, its wide…
Deep Variational Implicit Processes
Luis A. Ortega, Simón Rodríguez Santana, Daniel Hernández-Lobato
Implicit processes (IPs) are a generalization of Gaussian processes (GPs). IPs may lack a closed-form expression but are easy to sample from. Examples include, among others, Bayesi…
Diversity and Generalization in Neural Network Ensembles
Luis A. Ortega, Rafael Cabañas, Andrés R. Masegosa
Ensembles are widely used in machine learning and, usually, provide state-of-the-art performance in many prediction tasks. From the very beginning, the diversity of an ensemble has…