no code implementations • 15 Feb 2019 • Efi Kokiopoulou, Anja Hauth, Luciano Sbaiz, Andrea Gesmundo, Gabor Bartok, Jesse Berent
At the core of our framework lies a deep value network that can predict the performance of input architectures on a task by utilizing task meta-features and the previous model training experiments performed on related tasks.
no code implementations • 25 Sep 2019 • Krzysztof Maziarz, Efi Kokiopoulou, Andrea Gesmundo, Luciano Sbaiz, Gabor Bartok, Jesse Berent
We propose the Gumbel-Matrix routing, a novel multi-task routing method based on the Gumbel-Softmax, that is designed to learn fine-grained parameter sharing.
no code implementations • 10 Oct 2019 • Krzysztof Maziarz, Efi Kokiopoulou, Andrea Gesmundo, Luciano Sbaiz, Gabor Bartok, Jesse Berent
The binary allocation variables are learned jointly with the model parameters by standard back-propagation thanks to the Gumbel-Softmax reparametrization method.
Ranked #1 on Multi-Task Learning on OMNIGLOT
no code implementations • 26 Nov 2019 • Alina Dubatovka, Efi Kokiopoulou, Luciano Sbaiz, Andrea Gesmundo, Gabor Bartok, Jesse Berent
However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enables efficient architecture search by forecasting the performance of candidate architectures, instead of relying on actual model training.
no code implementations • ICLR 2021 • Thomas Fischbacher, Luciano Sbaiz
Quantum computing-based machine learning mainly focuses on quantum computing hardware that is experimentally challenging to realize due to requiring quantum gates that operate at very low temperature.
no code implementations • 10 Oct 2020 • Qifei Wang, Junjie Ke, Joshua Greaves, Grace Chu, Gabriel Bender, Luciano Sbaiz, Alec Go, Andrew Howard, Feng Yang, Ming-Hsuan Yang, Jeff Gilbert, Peyman Milanfar
This approach effectively reduces the total number of parameters and FLOPS, encouraging positive knowledge transfer while mitigating negative interference across domains.