Summary
ABOUT ME:
I am currently a postdoctoral researcher at Imperial College in London. Before this I was a postdoc at the CWI (Centrum Wiskunde & Informatica) in Amsterdam. My research interests are in optimization and applied probability and the applications of these topics in machine learning, privacy, and explainability.
I obtained my PhD cum laude from the University of Bologna in Financial Mathematics as part of a Marie-Curie ITN-EID project. I have obtained my Master's degree in Quantitative Finance at the VU Amsterdam and my Bachelor's degree in Applied Mathematics from the Delft University of Technology.
My personal webpage can be found here
My current research projects:
Robust optimization: Exploit tools from optimization and sampling to obtain convergence guarantees for (distributed) optimization algorithms and design robust algorithms. Applications include: deep neural networks.
Distributed optimization: In a setting where data is distributed across devices or servers we are interested in how to define the information exchange to balance communication costs and convergence speed.
Privacy guarantees: Design learning algorithms which do not leak sensitive information about the users and are safe and trustworthy.
Human intelligence: Applications of interest include anything from human-machine interactions to neuroscience and psychology.
Publications
Journals
Liu S, Borovykh A, Grzelak LA, et al. , 2019, A neural network-based framework for financial model calibration, Journal of Mathematics in Industry, Vol:9, ISSN:2190-5983