Výsledky vyhledávání - "Ordóñez, Sergio"

Report

Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel

Autor: Calvo-Ordoñez, Sergio, Palla, Konstantina, Ciosek, Kamil

Recent work has shown that training wide neural networks with gradient descent is formally equivalent to computing the mean of the posterior distribution in a Gaussian Process (GP) with the Neural Tangent Kernel (NTK) as the prior covariance and zero

Externí odkaz: http://arxiv.org/abs/2409.03953

Zobrazit plný text záznamu

Report

Uncertainty Modeling in Graph Neural Networks via Stochastic Differential Equations

Autor: Bergna, Richard, Calvo-Ordoñez, Sergio, Opolka, Felix L., Liò, Pietro, Hernandez-Lobato, Jose Miguel

We address the problem of learning uncertainty-aware representations for graph-structured data. While Graph Neural Ordinary Differential Equations (GNODE) are effective in learning node representations, they fail to quantify uncertainty. To address t

Externí odkaz: http://arxiv.org/abs/2408.16115

Zobrazit plný text záznamu

Report

Partially Stochastic Infinitely Deep Bayesian Neural Networks

Autor: Calvo-Ordonez, Sergio, Meunier, Matthieu, Piatti, Francesco, Shi, Yuantao

In this paper, we present Partially Stochastic Infinitely Deep Bayesian Neural Networks, a novel family of architectures that integrates partial stochasticity into the framework of infinitely deep neural networks. Our new class of architectures is de

Externí odkaz: http://arxiv.org/abs/2402.03495

Zobrazit plný text záznamu

Akademický článek

Global Production Networks and Dynamic Cores in the World’s Main Nodes : The Technological-Productive Transition of the Automotive Industry

Autor: Ordóñez, Sergio

Publikováno v: World Review of Political Economy, 2024 Apr 01. 15(1), 46-81.

Externí odkaz: https://www.jstor.org/stable/48774392

Zobrazit plný text záznamu

Report

The Missing U for Efficient Diffusion Models

Autor: Calvo-Ordonez, Sergio, Cheng, Chun-Wun, Huang, Jiahao, Zhang, Lipei, Yang, Guang, Schonlieb, Carola-Bibiane, Aviles-Rivero, Angelica I

Diffusion Probabilistic Models stand as a critical tool in generative modelling, enabling the generation of complex data distributions. This family of generative models yields record-breaking performance in tasks such as image synthesis, video genera

Externí odkaz: http://arxiv.org/abs/2310.20092

Zobrazit plný text záznamu