skip to content

The Engineering and Physical Sciences Research Council (EPSRC) awarded our postdoc Dr Yury Korolev with a three year Postdoctoral Fellowship to work on “Regularisation theory in the data driven setting”. Many congratulations Yury, we’re excited to have you in our group for a bit longer.

Yury obtained his doctorate from Moscow State University and since then has worked in Germany and the UK. His previous work was supported by a Humbold Fellowship and a Royal Society Newton International Fellowship. Yury's research interests are in the area of Applied Analysis, in particular in variational methods, inverse problems and theoretical data science.

In the forthcoming work, his goal is to extend regularisation theory to the setting where there is no direct access to the forward operator at the time of solving the inverse problem and only input-output training pairs are available. Such pairs can be either collected experimentally or obtained from a computationally expensive model prior to solving the inverse problem. The latter scenario is relevant for time-sensitive applications where near real-time reconstructions are required.  Furthermore, the model free setting is the natural habitat of neural networks, and his long-term goal is to better understand their regularisation properties in the context of ill-posed inverse problems in infinite dimensions.  The fellowship is due to start in April 2021.

For more information about Yury’s work please refer to his webpage