no code implementations • CVPR 2022 • Triantafyllos Afouras, Yuki M. Asano, Francois Fagan, Andrea Vedaldi, Florian Metze
We tackle the problem of learning object detectors without supervision.
no code implementations • 7 Aug 2018 • Francois Fagan, Garud Iyengar
Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate.
no code implementations • ICLR 2018 • Francois Fagan, Garud Iyengar
Recent neural network and language models rely on softmax distributions with an extremely large number of categories.
no code implementations • 19 Oct 2016 • Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Nourhan Sakr, Tamas Sarlos, Jamal Atif
We consider an efficient computational framework for speeding up several machine learning algorithms with almost no loss of accuracy.
no code implementations • 29 May 2016 • Krzysztof Choromanski, Francois Fagan, Cedric Gouy-Pailler, Anne Morvan, Tamas Sarlos, Jamal Atif
In particular, as a byproduct of the presented techniques and by using relatively new Berry-Esseen-type CLT for random vectors, we give the first theoretical guarantees for one of the most efficient existing LSH algorithms based on the $\textbf{HD}_{3}\textbf{HD}_{2}\textbf{HD}_{1}$ structured matrix ("Practical and Optimal LSH for Angular Distance").
no code implementations • 25 Apr 2016 • Krzysztof Choromanski, Francois Fagan
Our framework covers as special cases already known structured approaches such as the Fast Johnson-Lindenstrauss Transform, but is much more general since it can be applied also to highly nonlinear embeddings.