Tosca is a postdoctoral fellow at the Vector Institute, supervised by Dan Roy and Sivan Sabato. Before coming to Vector she completed her PhD at the University of Waterloo under the supervision of Shai Ben-David on “Inherent Limitations of Dimensions for Characterizing Learnability”. She has a Master’s degree in Cognitive Science from the University of University of Tübingen. She wrote her master thesis on “Domain Adaptation and Causal Assumptions” at the Max-Planck Institute for Intelligent Systems under the supervision of Professor Ruth Urner. Prior to that, she did my bachelor’s degree in Mathematics at Ludwig-Maximilians-Universität, Munich. She is interested in facilitating a better understanding of Machine Learning models and their limitations by means of a mathematical analysis. She aims to find intuitive assumptions that are meaningful in practice and lead to formal guarantees in scenarios in which common statistical assumptions break down, such as transfer learning. She believes that by developing tools that make the limitations of a model more explicit, it becomes easier to assess the trustworthiness of a model’s prediction. Her current research interests include adversarially and strategically robust learning, distribution learning, transfer learning and algorithmic fairness.