The browser you are using is not supported by this website. All versions of Internet Explorer are no longer supported, either by us or Microsoft (read more here: https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Please use a modern browser to fully experience our website, such as the newest versions of Edge, Chrome, Firefox or Safari etc.

New Thesis: Three questions for Johan Larsson

Photo of Johan Larsson

The thesis in statistics is titled ”Optimization and Algorithms in Sparse Regressions: Screening Rules, Coordinate Descent, and Normalization”, but what is it about?

"It is about statistical models for high-dimensional data, where the number of variables outnumber the number of observations, such as DNA microarray data where there may be hundreds of observations (patients) but millions of variables (gene expression indicators). 

In particular, it is about improving the optimization methods that are used when you fit these models to your data on your computer. In some cases our methods have enabled speed ups that amount to fitting the same model in seconds rather than hours." 

In three words, how would you describe your years as a PhD student at LUSEM?
"Fun, formative, and challenging!"

And what are you up to now?
"I am preparing for the defense and finalizing the last paper in my thesis, as well as looking forward to joining the Department of Mathematics in Copenhagen University as a post doc in the fall."
 

Thank you Johan, we wish you all the best, and take Copenhagen by storm!