This dissertation is devoted to nonparametric Bayesian label prediction on a graph. Label prediction is a problem within the area of statistical learning. Typically, we want to predict a label, i.e. the outcome of some quantitative or categorical measurement, based on some features of the available data. A training set of observed, possibly noisy, labels and the corresponding features is available to base our inference on. Label prediction problems on graphs arise in a variety of applications, for instance in machine learning, in the prediction of the biological function of a protein in a protein-protein interaction graph, in image analysis, and in the prediction of brand preference in social networks. Prime examples are problems in which t...
Structured output prediction is a machine learning tasks in which an input object is not just assign...
Abstract. Graphical model learning and inference are often performed using Bayesian techniques. In p...
Graphical models determine associations between variables through the notion of conditional independ...
An implementation of a nonparametric Bayesian approach to solving binary classification problems on ...
The adaptive processing of structured data is a long-standing research topic in machine learning tha...
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on...
AbstractMotivated by a problem of targeted advertising in social networks, we introduce a new model ...
Many real-world applications with graph data require the efficient solution of a given regression ta...
Motivated by a problem of targeted advertising in social networks, we introduce a new model of onlin...
Abstract. Bayes-N is an algorithm for Bayesian network learning from data based on local measures of...
Recently, techniques for applying convolutional neural networks to graph-structured data have emerge...
Classification of high dimensional data finds wide-ranging applications. In many of these applicatio...
We present a model for random simple graphs with power law (i.e., heavy-tailed) degree distributions...
We study the problem of online prediction of a noisy labeling of a graph with the perceptron. We add...
This thesis consists of four papers studying structure learning and Bayesian inference in probabilis...
Structured output prediction is a machine learning tasks in which an input object is not just assign...
Abstract. Graphical model learning and inference are often performed using Bayesian techniques. In p...
Graphical models determine associations between variables through the notion of conditional independ...
An implementation of a nonparametric Bayesian approach to solving binary classification problems on ...
The adaptive processing of structured data is a long-standing research topic in machine learning tha...
Graph-based semi-supervised regression (SSR) is the problem of estimating the value of a function on...
AbstractMotivated by a problem of targeted advertising in social networks, we introduce a new model ...
Many real-world applications with graph data require the efficient solution of a given regression ta...
Motivated by a problem of targeted advertising in social networks, we introduce a new model of onlin...
Abstract. Bayes-N is an algorithm for Bayesian network learning from data based on local measures of...
Recently, techniques for applying convolutional neural networks to graph-structured data have emerge...
Classification of high dimensional data finds wide-ranging applications. In many of these applicatio...
We present a model for random simple graphs with power law (i.e., heavy-tailed) degree distributions...
We study the problem of online prediction of a noisy labeling of a graph with the perceptron. We add...
This thesis consists of four papers studying structure learning and Bayesian inference in probabilis...
Structured output prediction is a machine learning tasks in which an input object is not just assign...
Abstract. Graphical model learning and inference are often performed using Bayesian techniques. In p...
Graphical models determine associations between variables through the notion of conditional independ...