Title: Machine Learning in Real World

Abstract: Machine learning (ML) with (deep) neural networks has gained tremendous recognition by academics and substantial industrial investments over a decade, which has led to a steady stream of advances such as enabling technologists to detect anomalies in medical images and providing high-accuracy translation between certain Pacific island and central African languages. Despite such early achievements, we are still far from harnessing ML’s full potentials of ML since: 1) the current learning theory does not answer how to achieve the minimum statistical risk under resource constraints and realistic settings; 2) the current set of practical tools to address resource constraints and realistic settings suffer from lack of generality and mainly focus on specific resource constraints and data-system perturbations.

Bio:

I am an Associate Professor (with tenure) in the Department of Informatics  at the  University of Oslo (UiO), a Principal Investigator at the Norwegian Center for Knowledge-driven Machine Learning (Integreat), and the SFI Visual Intelligence, and a member of the European Laboratory for Learning and Intelligent Systems (ELLIS) Society. I serve as an Area Chair of NeurIPS and AISTATS.

Before joining UiO, I was a Senior Scientific Collaborator at  EPFL , working with  Prof. Volkan Cevher  in  Laboratory for Information and Inference Systems (LIONS) . Before joining LIONS, I was an  NSERC Postdoctoral Fellow  at the  Vector Institute in Toronto working with  Prof. Daniel M. Roy . I received my Ph.D. from the  University of Toronto  where I was very fortunate to be advised by  Prof. Ben Liang  and  Prof. My Dong .