My research interests span the areas of artificial intelligence, machine learning, optimization, and high-performance computing. My team and I focus on advanced research areas in AI for Science at Argonne including scalable automated machine learning, metalearning, reinforcement learning, geometric machine learning, and neuromorphic computing.

I am a recipient of U.S. Department of Energy 2018 Early Career Award. I lead the AI area in RAPIDS2: A SciDAC Institute for Computer Science, Data, and Artificial Intelligence. I lead the research and development of DeepHyper, a scalable automated machine learning package for DOE leadership-class systems.

I am a Fellow in the Northwestern-Argonne Institute of Science and Engineering of the Northwestern University. I am also a Scientist At-large in the University of Chicago Consortium for Advanced Science and Engineering (UChicago CASE).

Previously,

• 2017--2020: Computer Scientist, MCS & LCF Divisions, Argonne National Laboratory
• 2014--2018: Fellow, Computation Institute, University of Chicago
• 2014--2017: Assistant Computer Scientist, MCS & LCF Divisions, Argonne National Laboratory
• 2010--2013: Postdoc, MCS Division, Argonne National Laboratory
• 2009--2010: Chief Technology Officer, Mentis SA, Brussels, Belgium

I received my PhD in 2010 from CoDE-IRIDIA (AI Lab), Université Libre de Bruxelles, Brussels, Belgium, where I was a recipient of Marie Skłodowska-Curie and F.R.S-FNRS Aspirant fellowships from the the European Commission and the Belgian-French Community's National Fund for Scientific Research, respectively.

News:

• PI on new DOE ASCR funded project with University of Southern California, Lawrence Berkeley National Laboratory, and UNC's Rennaisance Computing Institute: PosEiDon: Platform for Explainable Distributed Infrastructure. We will develop AI/ML based methods to simulate, model and optimize scientific workflow performance on large, distributed DOE computing infrastructures.
• Lead PI on new DOE EERE funded project with GE Resarch, GKN Aerospace, and Edison Welding Institute: Probabilistic Machine Learning for Rapid Large-Scale and High-Rate Aerostructure Manufacturing. We will develop a novel probabilistic ML framework to significantly improve manufacturing efficiency for large-scale aerostructures produced at high rates.
• [NeurIPS 2021] Formalizing the Generalization-Forgetting Trade-off in Continual Learning.
• [SC 2021] AgEBO-Tabular: Joint Neural Architecture and Hyperparameter Search with Autotuned Data-Parallel Training for Tabular Data.