Zobrazeno 1 - 10
of 26
pro vyhledávání: '"Bécigneul, Gary"'
Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown that when loo
Externí odkaz:
http://arxiv.org/abs/2406.10256
Autor:
Abraham, Louis, Becigneul, Gary, Coleman, Benjamin, Scholkopf, Bernhard, Shrivastava, Anshumali, Smola, Alexander
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 maximize information and minimize the number of tests? Group testing i
Externí odkaz:
http://arxiv.org/abs/2008.02641
Current graph neural network (GNN) architectures naively average or sum node embeddings into an aggregated graph representation -- potentially losing structural or semantic information. We here introduce OT-GNN, a model that computes graph embeddings
Externí odkaz:
http://arxiv.org/abs/2006.04804
We study the problem usually referred to as group testing in the context of COVID-19. Given $n$ samples taken from patients, how should we select mixtures of samples to be tested, so as to maximize information and minimize the number of tests? We con
Externí odkaz:
http://arxiv.org/abs/2005.06413
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 biases, e.g., hierarchical structures benefit from hyperbolic geometry.
Externí odkaz:
http://arxiv.org/abs/2002.08665
We develop a new Riemannian descent algorithm that relies on momentum to improve over existing first-order methods for geodesically convex optimization. In contrast, accelerated convergence rates proved in prior work have only been shown to hold for
Externí odkaz:
http://arxiv.org/abs/2002.04144
Publikováno v:
International Conference on Learning Representations (ICLR) 2020
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 geometric spaces with constant non-zero curvature improve representations and
Externí odkaz:
http://arxiv.org/abs/1911.08411
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 real-world data properties, e.g. scale-free, hierarchical or cyclical.
Externí odkaz:
http://arxiv.org/abs/1911.05076
We propose a novel second-order ODE as the continuous-time limit of a Riemannian accelerated gradient-based method on a manifold with curvature bounded from below. This ODE can be seen as a generalization of the ODE derived for Euclidean spaces, and
Externí odkaz:
http://arxiv.org/abs/1910.10782
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 independent of their corresponding inputs. We rely on calculus of variations a
Externí odkaz:
http://arxiv.org/abs/1907.10430