1,720,958 research outputs found
Applications de la théorie des matrices aléatoires en grandes dimensions et des probabilités libres en apprentissage statistique par réseaux de neurones
No full textThe functioning of machine learning algorithms relies heavily on the structure of the data they are given to study. Most research work in machine learning focuses on the study of homogeneous data, often modeled by independent and identically distributed random variables. However, data encountered in practice are often heterogeneous. In this thesis, we propose to consider heterogeneous data by endowing them with a variance profile. This notion, derived from random matrix theory, allows us in particular to study data arising from mixture models. We are particularly interested in the problem of ridge regression through two models: the linear ridge model and the random feature ridge model. In this thesis, we study the performance of these two models in the high-dimensional regime, i.e., when the size of the training sample and the dimension of the data tend to infinity at comparable rates. To this end, we propose asymptotic equivalents for the training error and the test error associated with the models of interest. The derivation of these equivalents relies heavily on spectral analysis from random matrix theory, free probability theory, and traffic theory. Indeed, the performance measurement of many learning models depends on the distribution of the eigenvalues of random matrices. Moreover, these results enabled us to observe phenomena specific to the high-dimensional regime, such as the double descent phenomenon. Our theoretical study is accompanied by numerical experiments illustrating the accuracy of the asymptotic equivalents we provide.Le fonctionnement des algorithmes d’apprentissage automatique repose grandement sur la structure des données qu’ils doivent utiliser. La majorité des travaux de recherche en apprentissage automatique se concentre sur l’étude de données homogènes, souvent modélisées par des variables aléatoires indépendantes et identiquement distribuées. Pourtant, les données apparaissant en pratique sont souvent hétérogènes. Nous proposons dans cette thèse de considérer des données hétérogènes en les dotant d’un profil de variance. Cette notion, issue de la théorie des matrices aléatoires, nous permet notamment d’étudier des données issues de modèles de mélanges. Nous nous intéressons plus particulièrement à la problématique de la régression ridge à travers deux modèles : la régression ridge linéaire (linear ridge model) et la régression ridge à caractéristiques aléatoires (random feature ridge model). Nous étudions dans cette thèse la performance de ces deux modèles dans le cadre de la grande dimension, c’est-à-dire lorsque la taille de l’échantillon d’entraînement et la dimension des données tendent vers l’infini avec des vitesses comparables. Dans cet objectif, nous proposons des équivalents asymptotiques de l’erreur d’entraînement et de l’erreur de test relatives aux modèles d’intérêt. L’obtention de ces équivalents repose grandement sur l’étude spectrale issue de la théorie des matrices aléatoires, des probabilités libres et de la théorie des trafics. En effet, la mesure de la performance de nombreux modèles d’apprentissage dépend de la distribution des valeurs propres de matrices aléatoires. De plus, ces résultats nous ont permis d’observer des phénomènes spécifiques à la grande dimension, comme le phénomène de la double descente. Notre étude théorique s’accompagne d’expériences numériques illustrant la précision des équivalents asymptotiques que nous fournissons
Applications of large-dimensional random matrix theory and free probability in statistical learning by neural networks
No full textLe fonctionnement des algorithmes d’apprentissage automatique repose grandement sur la structure des données qu’ils doivent utiliser. La majorité des travaux de recherche en apprentissage automatique se concentre sur l’étude de données homogènes, souvent modélisées par des variables aléatoires indépendantes et identiquement distribuées. Pourtant, les données apparaissant en pratique sont souvent hétérogènes. Nous proposons dans cette thèse de considérer des données hétérogènes en les dotant d’un profil de variance. Cette notion, issue de la théorie des matrices aléatoires, nous permet notamment d’étudier des données issues de modèles de mélanges. Nous nous intéressons plus particulièrement à la problématique de la régression ridge à travers deux modèles : la régression ridge linéaire (linear ridge model) et la régression ridge à caractéristiques aléatoires (random feature ridge model). Nous étudions dans cette thèse la performance de ces deux modèles dans le cadre de la grande dimension, c’est-à-dire lorsque la taille de l’échantillon d’entraînement et la dimension des données tendent vers l’infini avec des vitesses comparables. Dans cet objectif, nous proposons des équivalents asymptotiques de l’erreur d’entraînement et de l’erreur de test relatives aux modèles d’intérêt. L’obtention de ces équivalents repose grandement sur l’étude spectrale issue de la théorie des matrices aléatoires, des probabilités libres et de la théorie des trafics. En effet, la mesure de la performance de nombreux modèles d’apprentissage dépend de la distribution des valeurs propres de matrices aléatoires. De plus, ces résultats nous ont permis d’observer des phénomènes spécifiques à la grande dimension, comme le phénomène de la double descente. Notre étude théorique s’accompagne d’expériences numériques illustrant la précision des équivalents asymptotiques que nous fournissons.The functioning of machine learning algorithms relies heavily on the structure of the data they are given to study. Most research work in machine learning focuses on the study of homogeneous data, often modeled by independent and identically distributed random variables. However, data encountered in practice are often heterogeneous. In this thesis, we propose to consider heterogeneous data by endowing them with a variance profile. This notion, derived from random matrix theory, allows us in particular to study data arising from mixture models. We are particularly interested in the problem of ridge regression through two models: the linear ridge model and the random feature ridge model. In this thesis, we study the performance of these two models in the high-dimensional regime, i.e., when the size of the training sample and the dimension of the data tend to infinity at comparable rates. To this end, we propose asymptotic equivalents for the training error and the test error associated with the models of interest. The derivation of these equivalents relies heavily on spectral analysis from random matrix theory, free probability theory, and traffic theory. Indeed, the performance measurement of many learning models depends on the distribution of the eigenvalues of random matrices. Moreover, these results enabled us to observe phenomena specific to the high-dimensional regime, such as the double descent phenomenon. Our theoretical study is accompanied by numerical experiments illustrating the accuracy of the asymptotic equivalents we provide
High-dimensional analysis of ridge regression for non-identically distributed data with a variance profile
Full text linkHigh-dimensional linear regression has been thoroughly studied in the context
of independent and identically distributed data. We propose to investigate
high-dimensional regression models for independent but non-identically
distributed data. To this end, we suppose that the set of observed predictors
(or features) is a random matrix with a variance profile and with dimensions
growing at a proportional rate. Assuming a random effect model, we study the
predictive risk of the ridge estimator for linear regression with such a
variance profile. In this setting, we provide deterministic equivalents of this
risk and of the degree of freedom of the ridge estimator. For certain class of
variance profile, our work highlights the emergence of the well-known double
descent phenomenon in high-dimensional regression for the minimum norm
least-squares estimator when the ridge regularization parameter goes to zero.
We also exhibit variance profiles for which the shape of this predictive risk
differs from double descent. The proofs of our results are based on tools from
random matrix theory in the presence of a variance profile that have not been
considered so far to study regression models. Numerical experiments are
provided to show the accuracy of the aforementioned deterministic equivalents
on the computation of the predictive risk of ridge regression. We also
investigate the similarities and differences that exist with the standard
setting of independent and identically distributed data
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
