34 citations · 55 across the 12 of their papers we have counts for
9 papers · 1 filter
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…
The Jacobian and Hessian of the Kullback-Leibler Divergence between Multivariate Gaussian Distributions (Technical Report)
Juan Maroñas
This document shows how to obtain the Jacobian and Hessian matrices of the Kullback-Leibler divergence between two multivariate Gaussian distributions, using the first and second-o…
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…
Towards Efficient Modeling and Inference in Multi-Dimensional Gaussian Process State-Space Models
Zhidi Lin, Juan Maroñas, Ying Li +2
The Gaussian process state-space model (GPSSM) has attracted extensive attention for modeling complex nonlinear dynamical systems. However, the existing GPSSM employs separate Gaus…
Adaptive Temperature Scaling for Robust Calibration of Deep Neural Networks
Sergio A. Balanya, Juan Maroñas, Daniel Ramos
In this paper, we study the post-hoc calibration of modern neural networks, a problem that has drawn a lot of attention in recent years. Many calibration methods of varying complex…
Efficient Transformed Gaussian Processes for Non-Stationary Dependent Multi-class Classification
Juan Maroñas, Daniel Hernández-Lobato
This work introduces the Efficient Transformed Gaussian Process (ETGP), a new way of creating C stochastic processes characterized by: 1) the C processes are non-stationary, 2) the…
Transforming Gaussian Processes With Normalizing Flows
Juan Maroñas, Oliver Hamelijnck, Jeremias Knoblauch +1
Gaussian Processes (GPs) can be used as flexible, non-parametric function priors. Inspired by the growing body of work on Normalizing Flows, we enlarge this class of priors through…
On Calibration of Mixup Training for Deep Neural Networks
Juan Maroñas, Daniel Ramos, Roberto Paredes
Deep Neural Networks (DNN) represent the state of the art in many tasks. However, due to their overparameterization, their generalization capabilities are in doubt and still a fiel…
Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
Juan Maroñas, Roberto Paredes, Daniel Ramos
Deep Neural Networks (DNNs) have achieved state-of-the-art accuracy performance in many tasks. However, recent works have pointed out that the outputs provided by these models are…