Our paper titled “Accumulated Gradient Optimization” (J. Hermans, G. Spanakis, R. Moeckel) is accepted as a full paper at the 9th Asian Conference on Machine Learning (ACML2017).
This paper was first-authored by one of our Master in Artificial Intelligence graduates, based on his thesis work (started at CERN and awarded one of the best thesis awards from DKE for 2017).