no code implementations • 28 Oct 2023 • Fady Rezk
In this study, we start by conducting a systematic comparative analysis of the various approximation methods and their effect when incorporated into IML training routines.
no code implementations • 27 Oct 2023 • Fady Rezk, Antreas Antoniou, Henry Gouk, Timothy Hospedales
We analyze VeLO (versatile learned optimizer), the largest scale attempt to train a general purpose "foundational" optimizer to date.