Zobrazeno 1 - 10
of 72
pro vyhledávání: '"Ruiz, Francisco J. R."'
Autor:
Aglietti, Virginia, Ktena, Ira, Schrouff, Jessica, Sgouritsa, Eleni, Ruiz, Francisco J. R., Malek, Alan, Bellot, Alexis, Chiappa, Silvia
The sample efficiency of Bayesian optimization algorithms depends on carefully crafted acquisition functions (AFs) guiding the sequential collection of function evaluations. The best-performing AF can vary significantly across optimization problems,
Externí odkaz:
http://arxiv.org/abs/2406.04824
Publikováno v:
Transactions of the Association for Computational Linguistics, Vol 8, Pp 439-453 (2020)
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the embedded topic model (etm),
Externí odkaz:
https://doaj.org/article/d7eb59e1b2f64cca9c9d380df8cdc42e
Autor:
Ruiz, Francisco J. R., Laakkonen, Tuomas, Bausch, Johannes, Balog, Matej, Barekatain, Mohammadamin, Heras, Francisco J. H., Novikov, Alexander, Fitzpatrick, Nathan, Romera-Paredes, Bernardino, van de Wetering, John, Fawzi, Alhussein, Meichanetzidis, Konstantinos, Kohli, Pushmeet
A key challenge in realizing fault-tolerant quantum computers is circuit optimization. Focusing on the most expensive gates in fault-tolerant quantum computation (namely, the T gates), we address the problem of T-count optimization, i.e., minimizing
Externí odkaz:
http://arxiv.org/abs/2402.14396
A graph generative model defines a distribution over graphs. One type of generative model is constructed by autoregressive neural networks, which sequentially add nodes and edges to generate a graph. However, the likelihood of a graph under the autor
Externí odkaz:
http://arxiv.org/abs/2106.06189
Autor:
Richter, Lorenz, Boustati, Ayman, Nüsken, Nikolas, Ruiz, Francisco J. R., Akyildiz, Ömer Deniz
We analyse the properties of an unbiased gradient estimator of the ELBO for variational inference, based on the score function method with leave-one-out control variates. We show that this gradient estimator can be obtained using a new loss, defined
Externí odkaz:
http://arxiv.org/abs/2010.10436
Publikováno v:
Conference on Uncertainty in Artificial Intelligence (UAI, 2021)
The variational auto-encoder (VAE) is a deep latent variable model that has two neural networks in an autoencoder-like architecture; one of them parameterizes the model's likelihood. Fitting its parameters via maximum likelihood (ML) is challenging s
Externí odkaz:
http://arxiv.org/abs/2010.01845
We formulate meta learning using information theoretic concepts; namely, mutual information and the information bottleneck. The idea is to learn a stochastic representation or encoding of the task description, given by a training set, that is highly
Externí odkaz:
http://arxiv.org/abs/2009.03228
Generative adversarial networks (GANs) are a powerful approach to unsupervised learning. They have achieved state-of-the-art performance in the image domain. However, GANs are limited in two ways. They often learn distributions with low support---a p
Externí odkaz:
http://arxiv.org/abs/1910.04302
Topic modeling analyzes documents to learn meaningful patterns of words. For documents collected in sequence, dynamic topic models capture how these patterns vary over time. We develop the dynamic embedded topic model (D-ETM), a generative model of d
Externí odkaz:
http://arxiv.org/abs/1907.05545
Topic modeling analyzes documents to learn meaningful patterns of words. However, existing topic models fail to learn interpretable topics when working with large and heavy-tailed vocabularies. To this end, we develop the Embedded Topic Model (ETM),
Externí odkaz:
http://arxiv.org/abs/1907.04907