Our recent paper DOCTOR: A Simple Method for Detecting Misclassification Errors has been accepted as a spotlight presentation @ NeurIPS 2021. A huge congrats to my main coauthors: Pablo Piantanida who brilliantly supervised the project from the very beginning to the end, and Federica Granese whom I have been collaborating with since the beginning of my postdoc. Stay tuned!
Marco Romanelli
Research Associate
My research interests include applications of Information Theory notions to Privacy and Security, Safety in AI, Machine Learning and Information Leakage Measurement.