Guillermo Valle Pérez

14 papers A* 2Journal 11Unranked 1

Year	Rank	Type	Title / Venue / Authors
2024	A*	`conf`	Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes. AAAI Ouns El Harzli, Bernardo Cuenca Grau, Guillermo Valle Pérez, Ard A. Louis
2023	J	`jnl`	Do deep neural networks have an inbuilt Occam's razor? CoRR Chris Mingard, Henry Rees, Guillermo Valle Pérez, Ard A. Louis
2022	J	`jnl`	Evaluating language-biased image classification based on semantic representations. CoRR Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer
2022	A*	`conf`	Language-biased image classification: evaluation based on semantic representations. ICLR Yoann Lemesle, Masataka Sawayama, Guillermo Valle Pérez, Maxime Adolphe, Hélène Sauzéon, Pierre-Yves Oudeyer
2021	J	`jnl`	Double-descent curves in neural networks: a new perspective using Gaussian processes. CoRR Ouns El Harzli, Guillermo Valle Pérez, Ard A. Louis
2021	J	`jnl`	Is SGD a Bayesian sampler? Well, almost. J. Mach. Learn. Res. Chris Mingard, Guillermo Valle Pérez, Joar Skalse, Ard A. Louis
2021	J	`jnl`	Transflower: probabilistic autoregressive dance generation with multimodal attention. CoRR Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
2021	J	`jnl`	Transflower: probabilistic autoregressive dance generation with multimodal attention. ACM Trans. Graph. Guillermo Valle Pérez, Gustav Eje Henter, Jonas Beskow, Andre Holzapfel, Pierre-Yves Oudeyer, Simon Alexanderson
2021	J	`jnl`	Why Flatness Correlates With Generalization For Deep Neural Networks. CoRR Shuofeng Zhang, Isaac Reid, Guillermo Valle Pérez, Ard A. Louis
2020	J	`jnl`	Generalization bounds for deep learning. CoRR Guillermo Valle Pérez, Ard A. Louis
2020	J	`jnl`	Is SGD a Bayesian sampler? Well, almost. CoRR Chris Mingard, Guillermo Valle Pérez, Joar Skalse, Ard A. Louis
2019	—	`conf`	Deep learning generalizes because the parameter-function map is biased towards simple functions. ICLR (Poster) Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis
2019	J	`jnl`	Neural networks are a priori biased towards Boolean functions with low entropy. CoRR Chris Mingard, Joar Skalse, Guillermo Valle Pérez, David Martínez-Rubio, Vladimir Mikulik, Ard A. Louis
2018	J	`jnl`	Deep learning generalizes because the parameter-function map is biased towards simple functions. CoRR Guillermo Valle Pérez, Chico Q. Camargo, Ard A. Louis