Timezone: »

 
Poster
Anderson Acceleration of Proximal Gradient Methods
Vien Mai · Mikael Johansson

Thu Jul 16 02:00 PM -- 02:45 PM & Fri Jul 17 01:00 AM -- 01:45 AM (PDT) @ None #None

Anderson acceleration is a well-established and simple technique for speeding up fixed-point computations with countless applications. This work introduces novel methods for adapting Anderson acceleration to proximal gradient algorithms. Under some technical conditions, we extend existing local convergence results of Anderson acceleration for smooth fixed-point mappings to the proposed non-smooth setting. We also prove analytically that it is in general, impossible to guarantee global convergence of native Anderson acceleration. We therefore propose a simple scheme for stabilization that combines the global worst-case guarantees of proximal gradient methods with the local adaptation and practical speed-up of Anderson acceleration. Finally, we provide the first applications of Anderson acceleration to non-Euclidean geometry.

Author Information

Vien Mai (KTH Royal Institute of Technology)
Mikael Johansson (KTH Royal Institute of Technology)

More from the Same Authors