no code implementations • 2 Oct 2020 • Laëtitia Shao, Max Moroz, Elad Eban, Yair Movshovitz-Attias
Instead of distilling a model end-to-end, we propose to split it into smaller sub-networks - also called neighbourhoods - that are then trained independently.
1 code implementation • 17 Jun 2020 • Shraman Ray Chaudhuri, Elad Eban, Hanhan Li, Max Moroz, Yair Movshovitz-Attias
Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run.