no code implementations • 10 Apr 2023 • Jonathan Wittmer, Jacob Badger, Hari Sundar, Tan Bui-Thanh
In this work, we propose a close-to-ideal scalable compression approach using autoencoders to eliminate the need for checkpointing and substantial memory storage, thereby reducing both the time-to-solution and memory requirements.
no code implementations • 5 Dec 2019 • Hwan Goh, Sheroze Sheriffdeen, Jonathan Wittmer, Tan Bui-Thanh
Further, this framework possesses an inherent adaptive optimization property that emerges through the learning of the posterior uncertainty.