50 citations · 70 across the 3 of their papers we have counts for
8 papers · 1 filter
Computationally Tractable Riemannian Manifolds for Graph Embeddings
Calin Cruceru, Gary Bécigneul, Octavian-Eugen Ganea
Representing graphs as sets of node embeddings in certain curved Riemannian manifolds has recently gained momentum in machine learning due to their desirable geometric inductive bi…
Mixed-curvature Variational Autoencoders
Ondrej Skopek, Octavian-Eugen Ganea, Gary Bécigneul
Euclidean geometry has historically been the typical "workhorse" for machine learning applications due to its power and simplicity. However, it has recently been shown that geometr…
Constant Curvature Graph Convolutional Networks
Gregor Bachmann, Gary Bécigneul, Octavian-Eugen Ganea
Interest has been rising lately towards methods representing data in non-Euclidean spaces, e.g. hyperbolic or spherical, that provide specific inductive biases useful for certain r…
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…
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…
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…