1 November 2010 in Revista chilena de literatura
El artículo examina las concepciones operantes del libro, la lectura y la literatura en Chile, entre 1810 y 1842. Describe la concepción enciclópedica y eminentemente política de lo literario en las dos primeras generaciones de criollos ilustrados y el modo como ella fue conformando un canon para la nueva nación. Contrasta luego el discurso de la utopía ilustrada (entendida como verdad prematura) sobre la lectura y el libro con testimonios sobre su realidad. Finalmente enfrenta ambas perspectivas y las vincula a la independencia de la literatura.
22 August 2025 in Journal of Artificial Intelligence Research
Formal XAI (explainable AI) is a growing area that focuses on computing explanations with mathematical guarantees for the decisions made by ML models. Inside formal XAI, one of the most studied cases is that of explaining the choices taken by decision trees, as they are traditionally deemed as one of the most interpretable classes of models. Recent work has focused on studying the computation of sufficient reasons, a kind of explanation in which given a decision tree T and an instance x, one explains the decision T (x) by providing a subset y of the features of x such that for any other instance z compatible with y, it holds that T (z) = T (x), intuitively meaning that the features in y are already enough to fully justify the classification of x by T. It has been argued, however, that sufficient reasons constitute a restrictive notion of explanation. For such a reason, the community has started to study their probabilistic counterpart, in which one requires that the probability of T (z) = T (x) must be at least some value δ ∈ (0, 1], where z is a random instance that is compatible with y. Our paper settles the computational complexity of δ-sufficient-reasons over decision trees, showing that both (1) finding δ-sufficient-reasons that are minimal in size, and (2) finding δ-sufficient-reasons that are minimal inclusion-wise, are computationally intractable. By doing this, we answer two open problems originally raised by Izza et al. (2021), and extend the hardness of explanations for Boolean circuits presented by Wäldchen et al. (2021) to the more restricted case of decision trees. Furthermore, we present sharp non-approximability results under a widely believed complexity hypothesis. On the positive side, we identify structural restrictions of decision trees that make the problem tractable.
1 June 2021 in Nueva revista del Pacífico
El artículo examina la recepción de La Araucana (1568-1590) por patriotas americanos y por figuras de la Independencia de Chile, que leyeron la obra como un documento histórico que enaltecía a los araucanos presentandolos como un pueblo heroico e indomable. A partir de esta recepción se inventa una tradición que vincula las luchas por la Independencia con la que llevaron a cabo los araucanos contra la Corona española. El artículo revisa la recepción de la obra de Ercilla entre la elite criolla, entre líderes militares e intelectuales de la Patria Vieja (1810-1814) y luego de la batalla de Chacabuco (1817-1828), también entre los miembros más prominentes de la generación de 1842. Además la recepción que tuvo entre naturalistas y viajeros. Simbólicamente se advierte en estas lecturas una glorificación idealizada de los araucanos y de sus principales héroes, generándose a partir de ellas un doble discurso, que, por una parte, los glorifica como ancestros libertarios de la nación, y, por otra, los invisibiliza y maltrata en cuanto sujetos reales con una cultura propia y diferente, planteando con una perspectiva asimilacionista que deben ser civilizados y dejar de ser lo que son, doble discurso que de alguna manera persiste hasta el día de hoy.
9 June 2025 in Proceedings of the ACM on Management of Data
Despite the wide use of k -Nearest Neighbors as classification models, their explainability properties remain poorly understood from a theoretical perspective. While nearest neighbors classifiers offer interpretability from a ''data perspective'', in which the classification of an input vector x is explained by identifying the vectors v 1 , ..., v k in the training set that determine the classification of x, we argue that such explanations can be impractical in high-dimensional applications, where each vector has hundreds or thousands of features and it is not clear what their relative importance is. Hence, we focus on understanding nearest neighbor classifications through a ''feature perspective'', in which the goal is to identify how the values of the features in x affect its classification. Concretely, we study abductive explanations such as ''minimum sufficient reasons'', which correspond to sets of features in x that are enough to guarantee its classification, and counterfactual explanations based on the minimum distance feature changes one would have to perform in x to change its classification. We present a detailed landscape of positive and negative complexity results for counterfactual and abductive explanations, distinguishing between discrete and continuous feature spaces, and considering the impact of the choice of distance function involved. Finally, we show that despite some negative complexity results, Integer Quadratic Programming and SAT solving allow for computing explanations in practice.
1 January 2006 in Universum (Talca)