RCRui Augusto da Costa

Rui Augusto da Costa

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Rui Augusto da Costa has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Aggregation in Ill-Conditioned Regression Models: A Comparison with Entropy-Based Methods

    by Ana Helena Tavares, Ana Silva, Tiago Freitas, Maria Costa, Pedro Macedo, Rui A. da Costa

    Despite the advances on data analysis methodologies in the last decades, most of the traditional regression methods cannot be directly applied to large-scale data. Although aggregation methods are especially designed to deal with large-scale data, their performance may be strongly reduced in ill-conditioned problems (due to collinearity issues). This work compares the performance of a recent approach based on normalized entropy, a concept from information theory and info-metrics, with bagging and magging, two well-established aggregation methods in the literature, providing valuable insights for applications in regression analysis with large-scale data. While the results reveal a similar performance between methods in terms of prediction accuracy, the approach based on normalized entropy largely outperforms the other methods in terms of precision accuracy, even considering a smaller number of groups and observations per group, which represents an important advantage in inference problems with large-scale data. This work also alerts for the risk of using the OLS estimator, particularly under collinearity scenarios, knowing that data scientists frequently use linear models as a simplified view of the reality in big data analysis, and the OLS estimator is routinely used in practice. Beyond the promising findings of the simulation study, our estimation and aggregation strategies show strong potential for real-world applications in fields such as econometrics, genomics, environmental sciences, and machine learning, where data challenges such as noise and ill-conditioning are persistent.


  • Open Access

    Hidden transition in multiplex networks

    by R. A. da Costa, G. J. Baxter, S. N. Dorogovtsev, J. F. F. Mendes

    Weak multiplex percolation generalizes percolation to multi-layer networks, represented as networks with a common set of nodes linked by multiple types (colors) of edges. We report a novel discontinuous phase transition in this problem. This anomalous transition occurs in networks of three or more layers without unconnected nodes, $P(0)=0$. Above a critical value of a control parameter, the removal of a tiny fraction $\Delta$ of nodes or edges triggers a failure cascade which ends either with the total collapse of the network, or a return to stability with the system essentially intact. The discontinuity is not accompanied by any singularity of the giant component, in contrast to the discontinuous hybrid transition which usually appears in such problems. The control parameter is the fraction of nodes in each layer with a single connection, $\Pi=P(1)$. We obtain asymptotic expressions for the collapse time and relaxation time, above and below the critical point $\Pi_c$, respectively. In the limit $\Delta\to0$ the total collapse for $\Pi>\Pi_\text{c}$ takes a time $T \propto 1/(\Pi-\Pi_\text{c})$, while there is an exponential relaxation below $\Pi_\text{c}$ with a relaxation time $\tau \propto 1/[\Pi_\text{c}-\Pi]$.

  • Open Access

    Hidden transition in multiplex networks

    by R. A. da Costa, G. J. Baxter, S. N. Dorogovtsev, J. F. F. Mendes

    Weak multiplex percolation generalizes percolation to multi-layer networks, represented as networks with a common set of nodes linked by multiple types (colors) of edges. We report a novel discontinuous phase transition in this problem. This anomalous transition occurs in networks of three or more layers without unconnected nodes, $$P(0)\,=\,0$$ P ( 0 ) = 0 . Above a critical value of a control parameter, the removal of a tiny fraction $$\Delta$$ Δ of nodes or edges triggers a failure cascade which ends either with the total collapse of the network, or a return to stability with the system essentially intact. The discontinuity is not accompanied by any singularity of the giant component, in contrast to the discontinuous hybrid transition which usually appears in such problems. The control parameter is the fraction of nodes in each layer with a single connection, $$\Pi \,=\,P(1)$$ Π = P ( 1 ) . We obtain asymptotic expressions for the collapse time and relaxation time, above and below the critical point $$\Pi _c$$ Π c , respectively. In the limit $$\Delta \rightarrow 0$$ Δ → 0 the total collapse for $$\Pi \,>\,\Pi _\text {c}$$ Π > Π c takes a time $$T \propto 1/(\Pi -\Pi _\text {c})$$ T ∝ 1 / ( Π - Π c ) , while there is an exponential relaxation below $$\Pi _\text {c}$$ Π c with a relaxation time $$\tau \propto 1/[\Pi _\text {c}-\Pi ]$$ τ ∝ 1 / [ Π c - Π ] .


  • Approximating nonbacktracking centrality and localization phenomena in large networks

    by G. Timár, R. A. da Costa, S. N. Dorogovtsev, J. F. F. Mendes

    Message-passing theories have proved to be invaluable tools in studying percolation, nonrecurrent epidemics, and similar dynamical processes on real-world networks. At the heart of the message-passing method is the nonbacktracking matrix, whose largest eigenvalue, the corresponding eigenvector, and the closely related nonbacktracking centrality play a central role in determining how the given dynamical model behaves. Here we propose a degree-class-based method to approximate these quantities using a smaller matrix related to the joint degree-degree distribution of neighboring nodes. Our findings suggest that in most networks, degree-degree correlations beyond nearest neighbor are actually not strong, and our first-order description already results in accurate estimates, particularly when message-passing itself is a good approximation to the original model in question, that is, when the number of short cycles in the network is sufficiently low. We show that localization of the nonbacktracking centrality is also captured well by our scheme, particularly in large networks. Our method provides an alternative to working with the full nonbacktracking matrix in very large networks where this may not be possible due to memory limitations.


  • Open Access

    Effect of Initial Configuration of Weights on Training and Function of Artificial Neural Networks

    by Ricardo J. Jesus, Mário L. Antunes, Rui A. da Costa, Sergey N. Dorogovtsev, José F. F. Mendes, Rui L. Aguiar

    The function and performance of neural networks are largely determined by the evolution of their weights and biases in the process of training, starting from the initial configuration of these parameters to one of the local minima of the loss function. We perform the quantitative statistical characterization of the deviation of the weights of two-hidden-layer feedforward ReLU networks of various sizes trained via Stochastic Gradient Descent (SGD) from their initial random configuration. We compare the evolution of the distribution function of this deviation with the evolution of the loss during training. We observed that successful training via SGD leaves the network in the close neighborhood of the initial configuration of its weights. For each initial weight of a link we measured the distribution function of the deviation from this value after training and found how the moments of this distribution and its peak depend on the initial weight. We explored the evolution of these deviations during training and observed an abrupt increase within the overfitting region. This jump occurs simultaneously with a similarly abrupt increase recorded in the evolution of the loss function. Our results suggest that SGD’s ability to efficiently find local minima is restricted to the vicinity of the random initial configuration of weights.


  • Open Access

    Filtering Statistics on Networks

    by G. J. Baxter, R. A. da Costa, S. N. Dorogovtsev, J. F. F. Mendes

    Compression, filtering, and cryptography, as well as the sampling of complex systems, can be seen as processing information. A large initial configuration or input space is nontrivially mapped to a smaller set of output or final states. We explored the statistics of filtering of simple patterns on a number of deterministic and random graphs as a tractable example of such information processing in complex systems. In this problem, multiple inputs map to the same output, and the statistics of filtering is represented by the distribution of this degeneracy. For a few simple filter patterns on a ring, we obtained an exact solution of the problem and numerically described more difficult filter setups. For each of the filter patterns and networks, we found three key numbers that essentially describe the statistics of filtering and compared them for different networks. Our results for networks with diverse architectures are essentially determined by two factors: whether the graphs structure is deterministic or random and the vertex degree. We find that filtering in random graphs produces much richer statistics than in deterministic graphs, reflecting the greater complexity of such graphs. Increasing the graph’s degree reduces this statistical richness, while being at its maximum at the smallest degree not equal to two. A filter pattern with a strong dependence on the neighbourhood of a node is much more sensitive to these effects.

  • Exotic critical behavior of weak multiplex percolation

    by G. J. Baxter, R. A. da Costa, S. N. Dorogovtsev, J. F. F. Mendes

    We describe the critical behavior of weak multiplex percolation, a generalization of percolation to multiplex or interdependent networks. A node can determine its active or inactive status simply by referencing neighboring nodes. This is not the case for the more commonly studied generalization of percolation to multiplex networks, the mutually connected clusters, which requires an interconnecting path within each layer between any two vertices in the giant mutually connected component. We study the emergence of a giant connected component of active nodes under the weak percolation rule, finding several nontypical phenomena. In two layers, the giant component emerges with a continuous phase transition, but with quadratic growth above the critical threshold. In three or more layers, a discontinuous hybrid transition occurs, similar to that found in the giant mutually connected component. In networks with asymptotically powerlaw degree distributions, defined by the decay exponent γ, the discontinuity vanishes but at γ=1.5 in three layers, more generally at γ=1+1/(M−1) in M layers.


  • Open Access

    Complex Distributions Emerging in Filtering and Compression

    by G. J. Baxter, R. A. da Costa, S. N. Dorogovtsev, J. F. F. Mendes

    In filtering, each output is produced by a certain number of different inputs. We explore the statistics of this degeneracy in an explicitly treatable filtering problem in which filtering performs the maximal compression of relevant information contained in inputs (arrays of zeros and ones). This problem serves as a reference model for the statistics of filtering and related sampling problems. The filter patterns in this problem conveniently allow a microscopic, combinatorial consideration. This allows us to find the statistics of outputs, namely the exact distribution of output degeneracies, for arbitrary input sizes. We observe that the resulting degeneracy distribution of outputs decays as e−clogαd with degeneracy d, where c is a constant and exponent α>1, i.e., faster than a power law. Importantly, its form essentially depends on the size of the input dataset, appearing to be closer to a power-law dependence for small dataset sizes than for large ones. We demonstrate that for sufficiently small input dataset sizes typical for empirical studies, this distribution could be easily perceived as a power law. We extend our results to filter patterns of various sizes and demonstrate that the shortest filter pattern provides the maximum informative representations of the inputs.


  • How Foreign Tourist Intermediaries Perceive and Sell a Destination

    by Ana Mano Gomes, Rui Augusto da Costa, António Carrizo Moreira

    Research on tourist destination images is vast and embraces many destinations, approaches, and methods. More attention has been given to the perspective of final customers, instead of the ones who sell the tourist products to them. This chapter aims to understand how foreign tourist intermediaries, from the top outbound countries, perceive and sell Portugal as a tourist destination. It aims also to analyze the travel motivations they expect Portugal can satisfy and the information sources used to collect information to create tourist products regarding this destination. Foreign tourist intermediaries have a very positive image of Portugal as a destination, associating it to a set of cognitive attributes and psychological motivations.

  • Open Access

    Death and civic pedagogy in the portuguese republican context: the funerals of “prominent dead” in the early decades of the XXth century/ Morte e pedagogia cívica no contexto republicano português: os funerais dos “grandes mortos” nas primeiras décadas do Século XX (Bilingual Edition)

    by Joaquim Pintassilgo, Rui Afonso Da Costa

    Pretendemos, com este texto, promover uma reflexão acerca da utilização pedagógica e cívica dos funerais de “cidadãos ilustres” durante o período republicano português (1910-1926). O culto cívico dos mortos surgiu ligado à afirmação dos Estados-Nação e, em particular, à reinvenção das memórias coletivas necessárias à sua legitimação e projeção para o futuro. Os “grandes mortos”, alvo de consagração cívica, resultam de um processo de idealização que relativiza os seus defeitos e realça as respetivas virtudes. A partir daí eles passam a ser um exemplo para o resto da comunidade. A forma como as cerimónias eram organizadas e coreografadas enfatiza o seu potencial pedagógico. Escolhemos os exemplos de Guerra Junqueiro, um poeta, e de Sacadura Cabral, um aviador militar, e selecionámos três dos mais importantes jornais diários da época: O Século, o Diário de Notícias e O Mundo.Palavras-chave: Pedagogia cívica; Culto dos mortos; Memória. AbstractThis text has the purpose to reflect upon the pedagogical and civic use of the funeral ceremonies of distinguished citizens during the Portuguese republican period (1910-1926). The civic cult of the dead emerged in connection with the affirmation of the new Nation-states and, particularly, with the reinvention of collective memories, indispensable both for its validation and for its future. The “great dead”, subject to civic consecration, went through a process of idealization that overlooked their flaws and emphasized their virtues. From then on, they were an example for the rest of the community. The way the ceremonies were organized and choreographed gave emphasis to their pedagogical potential. We chose the examples of Guerra Junqueiro, a poet, and Sacadura Cabral, a military airman, and we selected three of the most important newspapers of the time: O Século, Diário de Notícias and O Mundo.Keywords: civic pedagogy; cult of the dead; memory;ResumenTenemos la intención, con este texto, de promover una reflexión sobre el uso educativo y cívico de los funerales de "distinguidos ciudadanos" durante el período republicano portugués (1910-1926). El culto cívico de los muertos surgió ligado a la afirmación de los Estados-nación y, en particular, a la reinvención de las memorias colectivas necesarias para su legitimación y proyección para el futuro. Los "grandes muertos", objeto de consagración cívica, resultan de un proceso de idealización que relativiza sus defectos y realza las respectivas virtudes. A partir de ahí pasan a ser un ejemplo para el resto de la comunidad. La forma en que las ceremonias eran organizadas y coreografiadas enfatiza su potencial pedagógico. Hemos escogido los ejemplos de Guerra Junqueiro, un poeta, y de Sacadura Cabral, un aviador militar, y seleccionamos tres de los más importantes diarios de la época: O Século, Diário de Notícias y O Mundo.Palabras clave: Pedagogía cívica; Culto de los muertos; Memoria.Recebido