Timezone: »

 
Poster
Fixing Implicit Derivatives: Trust-Region Based Learning of Continuous Energy Functions
Chris Russell · Matteo Toso · Neill Campbell

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #19
in Algorithms -- Model Selection and Structure Learning »

We present a new technique for the learning of continuous energy functions that we refer to as Wibergian Learning. One common approach to inverse problems is to cast them as an energy minimisation problem, where the minimum cost solution found is used as an estimator of hidden parameters. Our new approach formally characterises the dependency between weights that control the shape of the energy function, and the location of minima, by describing minima as fixed points of optimisation methods. This allows for the use of gradient-based end-to- end training to integrate deep-learning and the classical inverse problem methods. We show how our approach can be applied to obtain state-of-the-art results in the diverse applications of tracker fusion and multiview 3D reconstruction.

Keywords: Deep Learning · Non-Convex Optimization · Algorithms -> Model Selection and Structure Learning; Optimization
[ Paper]  [ Poster] 

Author Information

Chris Russell (The Alan Turing Institute/ The University of Surrey)
Matteo Toso (University of Surrey)
Neill Campbell (University of Bath)

More from the Same Authors