Cris Salvi

Prior to joining Imperial, I obtained my PhD from the University of Oxford under the supervision of Prof. Terry Lyons.

My research focuses on the interplay between rough analysis (rough paths, regularity structures etc) and several areas of machine learning, in particular, deep learning and kernel methods. In practice, the resulting algorithms can be used to process and extract actionable information from high-dimensional/irregularly-sampled/sparsely-observed time series. I am also interested in hybrid approaches combining neural networks and differential equations (eg neural RDEs, neural SPDEs) for modelling and simulating complex dynamical systems evolving under the influence of randomness.