I am working in the Empirical Inference group as a Ph.D. student associated with the International Max Planck Research School for Intelligent Systems (IMPRS-IS). Currently I have two main research interests.
Theoretical questions in machine learning, with a particular focus in deep learning. Specifically I am using techniques from topics like "concentration inequalities", "optimal transport" and "tropical geometry" to provide a better theoretical understanding of so called "adversarial examples". Adversarial examples are specifically crafted modifications of real inputs (images, sounds, etc) that humans find indistinguishable from the original, but that are consistently misclassified by our programs. For example an image of a panda will be correctly classified but adding an imperceptible noise to it will lead the algorithm to classify it as a potato (Here it is possible to find a quick survey).
Moreover I am interested in the intersection between machine learning and bayesian statistics, in particular variational methods. Together with Isabel Valera we are investigating how to improve variational techniques, like variational autoencoders (VAE). We are following two main approaches, first trying to develop better priors and second extend the VAE to the case of heterogeneous data.
Machine Learning Deep Learning Mathematics Statistical Learning Theory Bayesian Statistics
Unser Ziel ist es, die Prinzipien von Wahrnehmen, Lernen und Handeln in autonomen Systemen zu verstehen, die mit komplexen Umgebungen interagieren. Das Verständnis wollen wir nutzen, um künstliche intelligente Systeme zu entwickeln.