Abstract. In this talk, I will start discussing the main challenges of the deployment of machine learning methods in real-world applications. Then, I will provide an overview of my research, where I aim to develop machine learning methods that are i) expressive to capture the complex statistical properties of real-world data; ii) robust to provide accurate uncertainty estimates on these properties; and ii) accountable to ensure fairness and interpretability. Here, I will enter into the details two of my main projects: describing first how to design machine learning methods for event data using temporal point processes; and second, how to handle biases in the data and enforce a fairness notion in the outcomes of decision making systems. Finally, I will briefly describe my research agenda towards a trustworthy use of machine learning in the real-world.
Biography. Isabel Valera is a Minerva research group leader at the Max Planck for Intelligent Systems (MPI-IS). Isabel obtained her PhD in 2014 and her MSc degree in 2012, both degrees in Multimedia and Communications from the University Carlos III in Madrid, Spain. After her PhD, she worked at the MPI for Software Systems as a postdoctoral fellow, under the supervision of Dr. Manuel Gomez Rodriguez; and at the University of Cambridge as an associated researcher, under the supervision of Prof. Ghahramani. She has held a German Humboldt Post-Doctoral Fellowship, and last year she was granted with a “Minerva fast track” research group from the Max Planck Society, Germany. On an annual basis, the Minerva fast track programme offers two outstanding female scientists a long-term career opportunity with the aim of establishing an own research group within an MPI.
