Dr. O. Öktem (KTH Royal Institute of Technology, Stockholm)
Monday, June 14, 2021 - 15:00
Online Event
Please see WIAS events for more information, --- ---
Seminar on Optimization, Control and Inverse Problems
This joint work with Jevgenjia Rudzusika (KTH), Sebastian Banert (Lund University) and Jonas Adler (DeepMind) introduces a framework for using deep-learning to accelerate optimisation solvers with convergence guarantees. The approach builds on ideas from the analysis of accelerated forward-backward schemes, like FISTA. Instead of the classical approach of proving convergence for a choice of parameters, such as a step-size, we show convergence whenever the update is chosen in a specific set. Rather than picking a point in this set through a handcrafted method, we train a deep neural network to pick the best update. The method is applicable to several smooth and non-smooth convex optimisation problems and it outperforms established accelerated solvers.
submitted by uyanik (jutta.lohse@wias-berlin.de, 030 20372587)