6 citations · 23 across the 10 of their papers we have counts for
10 papers
An Embarrassingly Simple Way to Optimize Orthogonal Matrices at Scale
Adrián Javaloy, Antonio Vergari
Orthogonality constraints are ubiquitous in robust and probabilistic machine learning. Unfortunately, current optimizers are computationally expensive and do not scale to problems…
How to Square Tensor Networks and Circuits Without Squaring Them
Lorenzo Loconte, Adrián Javaloy, Antonio Vergari
Squared tensor networks (TNs) and their extension as computational graphs--squared circuits--have been used as expressive distribution estimators, yet supporting closed-form margin…
DeCaFlow: A deconfounding causal generative model
Alejandro Almodóvar, Adrián Javaloy, Juan Parras +2
We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate c…
COPA: Comparing the incomparable in multi-objective model evaluation
Adrián Javaloy, Antonio Vergari, Isabel Valera
In machine learning (ML), we often need to choose one among hundreds of trained ML models at hand, based on various objectives such as accuracy, robustness, fairness or scalability…
Causal normalizing flows: from theory to practice
Adrián Javaloy, Pablo Sánchez-Martín, Isabel Valera
In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identi…
Learnable Graph Convolutional Attention Networks
Adrián Javaloy, Pablo Sanchez-Martin, Amit Levi +1
Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighboring nodes, or by apply…
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization
Adrián Javaloy, Maryam Meghdadi, Isabel Valera
A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, m…
RotoGrad: Gradient Homogenization in Multitask Learning
Adrián Javaloy, Isabel Valera
Multitask learning is being increasingly adopted in applications domains like computer vision and reinforcement learning. However, optimally exploiting its advantages remains a maj…
Relative gradient optimization of the Jacobian term in unsupervised deep learning
Luigi Gresele, Giancarlo Fissore, Adrián Javaloy +2
Learning expressive probabilistic models correctly describing the data is a ubiquitous problem in machine learning. A popular approach for solving it is mapping the observations in…
Lipschitz standardization for multivariate learning
Adrián Javaloy, Isabel Valera
Probabilistic learning is increasingly being tackled as an optimization problem, with gradient-based approaches as predominant methods. When modelling multivariate likelihoods, a u…