skip to content
 

What do regularisers do?

Presented by: 
Tuomo Valkonen University of Liverpool
Date: 
Thursday 2nd November 2017 - 17:20 to 18:10
Venue: 
INI Seminar Room 1
Abstract: 
Which regulariser is the best? Is any of them any good? Do they introduce artefacts? What other qualitative properties do they have? These are some questions, on which I want to shed some light of the early dawn. Specifically, I will firstly discuss recent work on natural conditions, based on an analytical study of a bilevel learning approach, to ensure that regularisation does indeed improve an image. Based on a more computational study, based on bilevel learning, I will also try to answer the question, which constructed regulariser is the best one. Secondly, I will discuss geometrical aspects of the solutions to higher-order regularised imaging problems.

[ The video of this talk is temporarily unavailable. Please try later. ]

University of Cambridge Research Councils UK
    Clay Mathematics Institute London Mathematical Society NM Rothschild and Sons