activity
20172020
most citedBreaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

4 citations · 10 across the 5 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG20202 cited

Bloom Origami Assays: Practical Group Testing

Louis Abraham, Gary Becigneul, Benjamin Coleman +3

We study the problem usually referred to as group testing in the context of COVID-19. Given n samples collected from patients, how should we select and test mixtures of samples to…

cs.LG2019

Noise Contrastive Variational Autoencoders

Octavian-Eugen Ganea, Yashas Annadani, Gary Bécigneul

We take steps towards understanding the "posterior collapse (PC)" difficulty in variational autoencoders (VAEs),~i.e. a degenerate optimum in which the latent codes become independ…

cs.LG20194 cited

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities

Octavian-Eugen Ganea, Sylvain Gelly, Gary Bécigneul +1

The Softmax function on top of a final linear layer is the de facto method to output probability distributions in neural networks. In many applications such as language models or t…

cs.LG2018

Riemannian Adaptive Optimization Methods

Gary Bécigneul, Octavian-Eugen Ganea

Several first order stochastic optimization methods commonly used in the Euclidean domain such as stochastic gradient descent (SGD), accelerated gradient descent or variance reduce…

cs.LG2018

Hyperbolic Neural Networks

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Hyperbolic spaces have recently gained momentum in the context of machine learning due to their high capacity and tree-likeliness properties. However, the representational power of…

cs.LG2018

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning. We here present a nov…