Correlated Chained Gaussian Processes for Datasets With Multiple Annotators.

The labeling process within a supervised learning task is usually carried out by an expert, which provides the ground truth (gold standard) for each sample. However, in many real-world applications, we typically have access to annotations provided by crowds holding different and unknown expertise levels. Learning from crowds (LFC) intends to configure machine learning paradigms in the presence of multilabelers, residing on two key assumptions: the labeler's performance does not depend on the input space, and independence among the annotators is imposed. Here, we propose the correlated chained Gaussian processes from the multiple annotators (CCGPMA) approach, which models each annotator's performance as a function of the input space and exploits the correlations among experts. Experimental results associated with classification and regression tasks show that our CCGPMA performs better modeling of the labelers' behavior, indicating that it consistently outperforms other state-of-the-art LFC approaches.

A Fully Natural Gradient Scheme for Improving Inference of the Heterogeneous Multioutput Gaussian Process Model.

A recent novel extension of multioutput Gaussian processes (GPs) handles heterogeneous outputs, assuming that each output has its own likelihood function. It uses a vector-valued GP prior to jointly model all likelihoods' parameters as latent functions drawn from a GP with a linear model of coregionalization (LMC) covariance. By means of an inducing points' framework, the model is able to obtain tractable variational bounds amenable to stochastic variational inference (SVI). Nonetheless, the strong conditioning between the variational parameters and the hyperparameters burdens the adaptive gradient optimization methods used in the original approach. To overcome this issue, we borrow ideas from variational optimization introducing an exploratory distribution over the hyperparameters, allowing inference together with the posterior's variational parameters through a fully natural gradient (NG) optimization scheme. Furthermore, in this work, we introduce an extension of the heterogeneous multioutput model, where its latent functions are drawn from convolution processes. We show that our optimization scheme can achieve better local optima solutions with higher test performance rates than adaptive gradient methods for both the LMC and the convolution process model. We also show how to make the convolutional model scalable by means of SVI and how to optimize it through a fully NG scheme. We compare the performance of the different methods over the toy and real databases.

Psicología de la justicia distributiva: antecedentes y tipos de estudios para su comprensión / The psychology of distributive justice: background and types of studies for its understanding / Psicología da justiça distributiva: antecedentes e tipos de estudos para sua compreessão

Debido al incremento del estudio de la justicia como un fenómeno social de interés para la psicología,se hace una revisión que precisa los antecedentes de la psicología social en el estudio de las distribuciones materiales individuales en diversas situaciones, y las limitaciones de los análisis derivados de dichos estudios. Además, se presentan las posibilidades de indagación de las decisiones distributivas en al menos tres tipos de estudios que se reseñan en amplias revisiones y finaliza con la presentación de una reflexión sobre un "contexto" experimental como nueva perspectiva para el estudio de la justicia distributiva. Desde ese contexto, se describe el término "decisiones distributivas", y se propone como alternativa metodológica la consideración de variables habitualmente utilizadas en el análisis de algunos procesos cognitivos de interés para la economía experimental y comportamental.

Due to the increased study of justice as a social phenomenon of interest to psychology, a revision is carried out to specify the social psychology background in the study of individual material distributions in various situations and the constraints derived from such studies. In addition, the possibilities of inquiry into allocation decisions in at least three types of studies summarized in extensive reviews are presented, and finally, there is a reflection about an experimental "context" as a new perspective for the study of distributive justice. From this context, the term "distributive decisions" is described and, as a methodological alternative, the consideration of variables commonly used for the analysis of cognitive processes of interest for experimental and behavioral economics is proposed.

Devido ao aumento do estudo da justiça como um fenômeno social de interesse para a psicologia se faz uma revisão que especifica os antecedentes da psicologia social no estudo das distribuições materiais individuais em diversas situações, e as limitações das análises derivadas desses estudos. Além disso, apresentam-se as possibilidades de indagação das decisões distributivas em pelo menos três tipos de estudos que são resenhados em amplas revisões e finaliza com a apresentação de uma reflexão sobre um "contexto" experimental como nova perspectiva para o estudo da justiça distributiva. Desde esse contexto, descreve-se o termo "decisões distributivas", e propõe-se como alternativa metodológica a consideração de variáveis habitualmente utilizadas na análise de alguns processos cognitivos de interesse para a economia experimental e comportamental.