Zobrazeno 1 - 10
of 613
pro vyhledávání: '"Munoz, Pablo"'
Latent space geometry provides a rigorous and empirically valuable framework for interacting with the latent variables of deep generative models. This approach reinterprets Euclidean latent spaces as Riemannian through a pull-back metric, allowing fo
Externí odkaz:
http://arxiv.org/abs/2408.07507
Tuning scientific and probabilistic machine learning models $-$ for example, partial differential equations, Gaussian processes, or Bayesian neural networks $-$ often relies on evaluating functions of matrices whose size grows with the data set or th
Externí odkaz:
http://arxiv.org/abs/2405.17277
We investigate a convective Brinkman--Forchheimer problem coupled with a heat equation. The investigated model considers thermal diffusion and viscosity depending on the temperature. We prove the existence of a solution without restriction on the dat
Externí odkaz:
http://arxiv.org/abs/2403.09872
Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained by a central server that orchestrates the FL training process through
Externí odkaz:
http://arxiv.org/abs/2312.17430
Bayesian neural networks often approximate the weight-posterior with a Gaussian distribution. However, practical posteriors are often, even locally, highly non-Gaussian, and empirical performance deteriorates. We propose a simple parametric approxima
Externí odkaz:
http://arxiv.org/abs/2306.07158
Masked pre-training removes random input dimensions and learns a model that can predict the missing values. Empirical results indicate that this intuitive form of self-supervised learning yields models that generalize very well to new domains. A theo
Externí odkaz:
http://arxiv.org/abs/2306.00520
Autor:
Solfiti, Emanuele, Wan, Di, Celotto, Ambra, Solieri, Nicola, Munoz, Pablo Andreu, Ximenes, Rui Franqueira, Heredia, Jorge Maestre, Martin, Claudio Leopoldo Torregrosa, Nuiry, Antonio Perillo Marcone Francois-Xavier, Alvaro, Antonio, Berto, Filippo, Calviani, Marco
Flexible graphite (FG) with 1 - 1.2 g/cm$^3$ density is employed as beam energy absorber material in the CERN's Large Hadron Collider (LHC) beam dumping system. However, the increase of energy deposited expected for new HL-LHC (High-Luminosity LHC) d
Externí odkaz:
http://arxiv.org/abs/2304.04021
In this paper, we investigate the relationship between diversity metrics, accuracy, and resiliency to natural image corruptions of Deep Learning (DL) image classifier ensembles. We investigate the potential of an attribution-based diversity metric to
Externí odkaz:
http://arxiv.org/abs/2303.09283
Decoders built on Gaussian processes (GPs) are enticing due to the marginalisation over the non-linear function space. Such models (also known as GP-LVMs) are often expensive and notoriously difficult to train in practice, but can be scaled using var
Externí odkaz:
http://arxiv.org/abs/2209.04636
Autor:
Miani, Marco, Warburg, Frederik, Moreno-Muñoz, Pablo, Detlefsen, Nicke Skafte, Hauberg, Søren
Established methods for unsupervised representation learning such as variational autoencoders produce none or poorly calibrated uncertainty estimates making it difficult to evaluate if learned representations are stable and reliable. In this work, we
Externí odkaz:
http://arxiv.org/abs/2206.15078