Zobrazeno 1 - 10
of 13 369
pro vyhledávání: '"D'Antonio G"'
Graph neural networks (GNNs) have emerged as a promising solution to deal with unstructured data, outperforming traditional deep learning architectures. However, most of the current GNN models are designed to work with a single graph, which limits th
Externí odkaz:
http://arxiv.org/abs/2411.05119
This work presents a low-rank tensor model for multi-dimensional Markov chains. A common approach to simplify the dynamical behavior of a Markov chain is to impose low-rankness on the transition probability matrix. Inspired by the success of these ma
Externí odkaz:
http://arxiv.org/abs/2411.02098
In this paper, we present XST-GCNN (eXplainable Spatio-Temporal Graph Convolutional Neural Network), a novel architecture for processing heterogeneous and irregular Multivariate Time Series (MTS) data. Our approach captures temporal and feature depen
Externí odkaz:
http://arxiv.org/abs/2411.01070
Graph learning is the fundamental task of estimating unknown graph connectivity from available data. Typical approaches assume that not only is all information available simultaneously but also that all nodes can be observed. However, in many real-wo
Externí odkaz:
http://arxiv.org/abs/2409.08760
Graph neural networks (GNNs) have become a workhorse approach for learning from data defined over irregular domains, typically by implicitly assuming that the data structure is represented by a homophilic graph. However, recent works have revealed th
Externí odkaz:
http://arxiv.org/abs/2409.08676
This paper introduces a probabilistic approach for tracking the dynamics of unweighted and directed graphs using state-space models (SSMs). Unlike conventional topology inference methods that assume static graphs and generate point-wise estimates, ou
Externí odkaz:
http://arxiv.org/abs/2409.08238
We study the problem of computing deterministic optimal policies for constrained Markov decision processes (MDPs) with continuous state and action spaces, which are widely encountered in constrained dynamical systems. Designing deterministic policy g
Externí odkaz:
http://arxiv.org/abs/2408.10015
Autor:
Escudero-Arnanz, Óscar, Soguero-Ruiz, Cristina, Álvarez-Rodríguez, Joaquín, Marques, Antonio G.
Antimicrobial Resistance represents a significant challenge in the Intensive Care Unit (ICU), where patients are at heightened risk of Multidrug-Resistant (MDR) infections-pathogens resistant to multiple antimicrobial agents. This study introduces a
Externí odkaz:
http://arxiv.org/abs/2407.17165
Autor:
Bello-Morales, Antonio G., Jiménez, Jose Beltrán, Cano, Alejandro Jiménez, Maroto, Antonio L., Koivisto, Tomi S.
Theories formulated in the arena of teleparallel geometries are generically plagued by ghost-like instabilities or other pathologies that are ultimately caused by the breaking of some symmetries. In this work, we construct a class of ghost-free theor
Externí odkaz:
http://arxiv.org/abs/2406.19355
Autor:
Jiang, Liuyuan, Xiao, Quan, Tenorio, Victor M., Real-Rojas, Fernando, Marques, Antonio G., Chen, Tianyi
Interest in bilevel optimization has grown in recent years, partially due to its applications to tackle challenging machine-learning problems. Several exciting recent works have been centered around developing efficient gradient-based algorithms that
Externí odkaz:
http://arxiv.org/abs/2406.10148