Search Results for author: Francois Fagan

Found 6 papers, 0 papers with code

Robust Implicit Backpropagation

no code implementations7 Aug 2018 Francois Fagan, Garud Iyengar

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate.

Unbiased scalable softmax optimization

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.

TripleSpin - a generic compact paradigm for fast machine learning computations

no code implementations29 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").

Quantization

Fast nonlinear embeddings via structured matrices

no code implementations25 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.