Gary Bécigneul

According to our database, Gary Bécigneul authored at least 17 papers between 2017 and 2021.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2021

On the Geometry of Data Representations.

Gary Bécigneul

PhD thesis, 2021

Environment and Speaker Related Emotion Recognition in Conversations.

Zebin Zhong, Shiqi Yang, Gary Bécigneul

Proceedings of the CONF-CDS 2021: The 2nd International Conference on Computing and Data Science, 2021

Momentum Improves Optimization on Riemannian Manifolds.

Foivos Alimisis, Antonio Orvieto, Gary Bécigneul, Aurélien Lucchi

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

Computationally Tractable Riemannian Manifolds for Graph Embeddings.

Calin Cruceru, Gary Bécigneul, Octavian-Eugen Ganea

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Bloom Origami Assays: Practical Group Testing.

Louis Abraham, Gary Bécigneul, Benjamin Coleman, Bernhard Schölkopf, Anshumali Shrivastava, Alexander J. Smola

CoRR, 2020

Optimal Transport Graph Neural Networks.

Gary Bécigneul, Octavian-Eugen Ganea, Benson Chen, Regina Barzilay, Tommi S. Jaakkola

CoRR, 2020

Crackovid: Optimizing Group Testing.

Louis Abraham, Gary Bécigneul, Bernhard Schölkopf

CoRR, 2020

Constant Curvature Graph Convolutional Networks.

Gregor Bachmann, Gary Bécigneul, Octavian Ganea

Proceedings of the 37th International Conference on Machine Learning, 2020

Mixed-curvature Variational Autoencoders.

Ondrej Skopek, Octavian-Eugen Ganea, Gary Bécigneul

Proceedings of the 8th International Conference on Learning Representations, 2020

A Continuous-time Perspective for Modeling Acceleration in Riemannian Optimization.

Foivos Alimisis, Antonio Orvieto, Gary Bécigneul, Aurélien Lucchi

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, 2020

2019

Breaking the Softmax Bottleneck via Learnable Monotonic Pointwise Non-linearities.

Octavian Ganea, Sylvain Gelly, Gary Bécigneul, Aliaksei Severyn

Proceedings of the 36th International Conference on Machine Learning, 2019

Poincare Glove: Hyperbolic Word Embeddings.

Alexandru Tifrea, Gary Bécigneul, Octavian-Eugen Ganea

Proceedings of the 7th International Conference on Learning Representations, 2019

Riemannian Adaptive Optimization Methods.

Gary Bécigneul, Octavian-Eugen Ganea

Proceedings of the 7th International Conference on Learning Representations, 2019

2018

Hyperbolic Neural Networks.

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Hyperbolic Entailment Cones for Learning Hierarchical Embeddings.

Octavian-Eugen Ganea, Gary Bécigneul, Thomas Hofmann

Proceedings of the 35th International Conference on Machine Learning, 2018

2017

Parametrizing filters of a CNN with a GAN.

Yannic Kilcher, Gary Bécigneul, Thomas Hofmann

CoRR, 2017

On the effect of pooling on the geometry of representations.

Gary Bécigneul

CoRR, 2017