no code implementations • 9 Nov 2023 • Akrit Mudvari, Antero Vainio, Iason Ofeidis, Sasu Tarkoma, Leandros Tassiulas
In this work, we develop an adaptive compression-aware split learning method ('deprune') to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources.
no code implementations • 17 May 2023 • Georgios Palaiokrassas, Sandro Scherrers, Iason Ofeidis, Leandros Tassiulas
Since the inception of permissionless blockchains with Bitcoin in 2008, it became apparent that their most well-suited use case is related to making the financial system and its advantages available to everyone seamlessly without depending on any trusted intermediaries.
no code implementations • 20 Feb 2023 • Antzelos Kyriazis, Iason Ofeidis, Georgios Palaiokrassas, Leandros Tassiulas
We also show that some borrowing interest rates in the Ethereum DeFi ecosystem are affected positively by unexpected changes in monetary policy.
no code implementations • 27 Sep 2022 • Iason Ofeidis, Diego Kiedanski, Leandros Tassiulas
Dataloaders, in charge of moving data from storage into GPUs while training machine learning models, might hold the key to drastically improving the performance of training jobs.