Guillermo Valle Pérez

According to our database, Guillermo Valle Pérez authored at least 11 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes.

Ouns El Harzli, Bernardo Cuenca Grau, Guillermo Valle Pérez, Ard A. Louis

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Do deep neural networks have an inbuilt Occam's razor?

Chris Mingard, Henry Rees, Guillermo Valle Pérez, Ard A. Louis

CoRR, 2023

2022

Evaluating language-biased image classification based on semantic representations.

Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer

CoRR, 2022

Language-biased image classification: evaluation based on semantic representations.

Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Transflower: probabilistic autoregressive dance generation with multimodal attention.

Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson

ACM Trans. Graph., 2021

Is SGD a Bayesian sampler? Well, almost.

Chris Mingard, Guillermo Valle Pérez, Joar Skalse, Ard A. Louis

J. Mach. Learn. Res., 2021

Why Flatness Correlates With Generalization For Deep Neural Networks.

Shuofeng Zhang, Isaac Reid, Guillermo Valle Pérez, Ard A. Louis

CoRR, 2021

Double-descent curves in neural networks: a new perspective using Gaussian processes.

Ouns El Harzli, Guillermo Valle Pérez, Ard A. Louis

CoRR, 2021

2020

Generalization bounds for deep learning.

Guillermo Valle Pérez, Ard A. Louis

CoRR, 2020

2019

Neural networks are a priori biased towards Boolean functions with low entropy.

Chris Mingard, Joar Skalse, Guillermo Valle Pérez, David Martínez-Rubio, Vladimir Mikulik, Ard A. Louis

CoRR, 2019

Deep learning generalizes because the parameter-function map is biased towards simple functions.

Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis

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