AG Mathematics of Deep Learning – Jevgenija Rudzusika (KTH Royal Institute of Technology, Stockholm, Sweden)

Datum: 20-07-2021Zeit: 12:15 – 13:45Ort: Online

Title: Accelerated Forward-Backward Optimization using Deep Learningt

Abstract: We propose several deep-learning accelerated optimization solvers with convergence guarantees. We use ideas from the analysis of accelerated forward-backward schemes like FISTA, but 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 using some predefined method, we train a deep neural network to pick the best update. Finally, we show that the method is applicable to several cases of smooth and non-smooth optimization and show superior results to established accelerated solvers.

Zum Kalender hinzufügen

Details

Datum:
20-07-2021
Zeit:
12:15 – 13:45
Ort:

Online

Veranstaltungskategorien:
Invprob-Vortraege