Zobrazeno 1 - 10
of 638
pro vyhledávání: '"Haddouche, A"'
Autor:
Haddouche, Anis M., Lu, Wei
Publikováno v:
Comptes Rendus. Mathématique, Vol 360, Iss G10, Pp 1093-1098 (2022)
In this paper, we address the problem of estimating a covariance matrix of a multivariate Gaussian distribution, from a decision theoretic point of view, relative to a Stein type loss function. We investigate the case where the covariance matrix is i
Externí odkaz:
https://doaj.org/article/650b678038c24580b0750357c60ec884
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
We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset with respect to the other nodes.
Externí odkaz:
http://arxiv.org/abs/2310.11203
Minimising upper bounds on the population risk or the generalisation gap has been widely used in structural risk minimisation (SRM) -- this is in particular at the core of PAC-Bayesian learning. Despite its successes and unfailing surge of interest i
Externí odkaz:
http://arxiv.org/abs/2306.04375
Autor:
Haddouche, Maxime, Guedj, Benjamin
PAC-Bayes learning is an established framework to both assess the generalisation ability of learning algorithms, and design new learning algorithm by exploiting generalisation bounds as training objectives. Most of the exisiting bounds involve a \emp
Externí odkaz:
http://arxiv.org/abs/2304.07048
Optimistic Online Learning algorithms have been developed to exploit expert advices, assumed optimistically to be always useful. However, it is legitimate to question the relevance of such advices \emph{w.r.t.} the learning information provided by gr
Externí odkaz:
http://arxiv.org/abs/2301.07530
Publikováno v:
Revue des Énergies Renouvelables, Pp 189 – 197-189 – 197 (2024)
In this study, we present an autonomous solution for a village located north of Timimoun in Algeria, with around thirty households. As the region has good wind potential with an average annual speed of around 5m/s, this resource is used to develop a
Externí odkaz:
https://doaj.org/article/087afb01ddec4ee0877983ea72a1e40e
Publikováno v:
Revue des Énergies Renouvelables, Pp 209 – 214-209 – 214 (2024)
The majority of countries worldwide rely on fossil fuels as a source of energy. Nevertheless, the utilization of this source of energy is associated with significant environmental problems. To reduce their impact, innovative clean energy solutions ar
Externí odkaz:
https://doaj.org/article/53b45203463f457ca1780460446e7fcd
Autor:
Haddouche, Maxime, Guedj, Benjamin
While PAC-Bayes is now an established learning framework for light-tailed losses (\emph{e.g.}, subgaussian or subexponential), its extension to the case of heavy-tailed losses remains largely uncharted and has attracted a growing interest in recent y
Externí odkaz:
http://arxiv.org/abs/2210.00928