Zobrazeno 1 - 10
of 6 817
pro vyhledávání: '"A Guedj"'
The clearance of explosive remnants of war (ERW) continues to be a predominantly manual and high-risk process that can benefit from advances in technology to improve its efficiency and effectiveness. In particular, research on artificial intelligence
Externí odkaz:
http://arxiv.org/abs/2411.05813
Publikováno v:
Neurips 2024, Dec 2024, Vancouver, Canada
PAC-Bayes learning is a comprehensive setting for (i) studying the generalisation ability of learning algorithms and (ii) deriving new learning algorithms by optimising a generalisation bound. However, optimising generalisation bounds might not alway
Externí odkaz:
http://arxiv.org/abs/2410.10230
We consider time-series forecasting problems where data is scarce, difficult to gather, or induces a prohibitive computational cost. As a first attempt, we focus on short-term electricity consumption in France, which is of strategic importance for en
Externí odkaz:
http://arxiv.org/abs/2409.05934
Autor:
Dieny, Bernard, Aggarwal, Sanjeev, Naik, Vinayak Bharat, Couet, Sebastien, Coughlin, Thomas, Fukami, Shunsuke, Garello, Kevin, Guedj, Jack, Incorvia, Jean Anne C., Lebrun, Laurent, Lee, Kyung-Jin, Leonelli, Daniele, Noh, Yonghwan, Salimy, Siamak, Soss, Steven, Thomas, Luc, Wang, Weigang, Worledge, Daniel
This application note discusses the working principle of spin-transfer torque magnetoresistive random access memory (STT-MRAM) and the impact that magnetic fields can have on STT-MRAM operation. Sources of magnetic field and typical magnitudes of mag
Externí odkaz:
http://arxiv.org/abs/2409.05584
We study the volumes of transcendental and possibly non-closed Bott-Chern $(1,1)$-classes on an arbitrary compact complex manifold $X$. We show that the latter belongs to the class $\mathcal{C}$ of Fujiki if and only if it has the $\textit{bounded ma
Externí odkaz:
http://arxiv.org/abs/2406.01090
Publikováno v:
Bioresource Technology 2023
Uncertainty quantification is critical for ensuring adequate predictive power of computational models used in biology. Focusing on two anaerobic digestion models, this article introduces a novel generalized Bayesian procedure, called VarBUQ, ensuring
Externí odkaz:
http://arxiv.org/abs/2405.19824
Autor:
Guedj, Vincent, Tô, Tat Dat
In a remarkable series of works, Guo, Phong, Song, and Sturm have obtained key uniform estimates for the Green's functions associated with certain K\"ahler metrics. In this note, we broaden the scope of their techniques by removing one of their assum
Externí odkaz:
http://arxiv.org/abs/2405.17232
Sequential Bayesian Filtering aims to estimate the current state distribution of a Hidden Markov Model, given the past observations. The problem is well-known to be intractable for most application domains, except in notable cases such as the tabular
Externí odkaz:
http://arxiv.org/abs/2402.09796
Modern machine learning usually involves predictors in the overparametrised setting (number of trained parameters greater than dataset size), and their training yield not only good performances on training data, but also good generalisation capacity.
Externí odkaz:
http://arxiv.org/abs/2402.08508
This paper contains a recipe for deriving new PAC-Bayes generalisation bounds based on the $(f, \Gamma)$-divergence, and, in addition, presents PAC-Bayes generalisation bounds where we interpolate between a series of probability divergences (includin
Externí odkaz:
http://arxiv.org/abs/2402.05101