Guillermo Valle-Pérez

4 papers · 2019–2024 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🏃 Academic Marathon (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15) ❓ The Questioner

Conferences

ICLR (2) AAAI (1) JMLR (1)

Top co-authors

Ard A. Louis (3) Yoann Lemesle (1) Masataka Sawayama (1) Chris Mingard (1) Pierre-yves Oudeyer (1) Chico Q. Camargo (1) Ouns El Harzli (1) Joar Skalse (1) Bernardo Cuenca Grau (1) Maxime Adolphe (1)

Keywords

stochastic gradient descent (1) gaussian process (1) generalization error (1) kernel regression (1) bayesian posterior (1) random matrix theory (1) deep neural network (1) feature covariance (1) overparameterized regime (1) neural network (1) double-descent curve (1)

Papers

Double-Descent Curves in Neural Networks: A New Perspective Using Gaussian Processes AAAI 2024

Language-biased image classification: evaluation based on semantic representations ICLR 2022

Is SGD a Bayesian sampler? Well, almost JMLR 2021

Deep learning generalizes because the parameter-function map is biased towards simple functions ICLR 2019