Zobrazeno 1 - 10
of 827
pro vyhledávání: '"Alquier P"'
Autor:
Khribch, El Mahdi, Alquier, Pierre
Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory, and Bayesian nonparametrics. This work introduces a novel mutual information bound for statistical models.
Externí odkaz:
http://arxiv.org/abs/2412.18539
Autor:
Alquier, Pierre, Kengne, William
In a groundbreaking work, Schmidt-Hieber (2020) proved the minimax optimality of deep neural networks with ReLu activation for least-square regression estimation over a large class of functions defined by composition. In this paper, we extend these r
Externí odkaz:
http://arxiv.org/abs/2410.21702
Publikováno v:
Dependence Modeling, Vol 7, Iss 1, Pp 150-168 (2019)
Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on inequalities an
Externí odkaz:
https://doaj.org/article/61e5d6f6c19342198b369bbc61b7f097
This work investigates the offline formulation of the contextual bandit problem, where the goal is to leverage past interactions collected under a behavior policy to evaluate, select, and learn new, potentially better-performing, policies. Motivated
Externí odkaz:
http://arxiv.org/abs/2405.14335
Autor:
Wolfer, Geoffrey, Alquier, Pierre
The convergence rate of a Markov chain to its stationary distribution is typically assessed using the concept of total variation mixing time. However, this worst-case measure often yields pessimistic estimates and is challenging to infer from observa
Externí odkaz:
http://arxiv.org/abs/2402.10506
Autor:
Greco, Giuseppe, Fiorenza, Patrick, Schilirò, Emanuela, Bongiorno, Corrado, Di Franco, Salvatore, Coulon, Pierre-Marie, Frayssinet, Eric, Bartoli, Florian, Giannazzo, Filippo, Alquier, Daniel, Cordier, Yvon, Roccaforte, Fabrizio
In this paper, the Ni Schottky barrier on GaN epilayer grown on free standing substrates has been characterized. First, transmission electrical microscopy (TEM) images and nanoscale electrical analysis by conductive atomic force microscopy (C-AFM) of
Externí odkaz:
http://arxiv.org/abs/2304.11680
Bernstein's condition is a key assumption that guarantees fast rates in machine learning. For example, the Gibbs algorithm with prior $\pi$ has an excess risk in $O(d_{\pi}/n)$, as opposed to the standard $O(\sqrt{d_{\pi}/n})$, where $n$ denotes the
Externí odkaz:
http://arxiv.org/abs/2302.11709
Publikováno v:
Dependence Modeling, Vol 1, Iss 2013, Pp 65-93 (2013)
We establish rates of convergences in statistical learning for time series forecasting. Using the PAC-Bayesian approach, slow rates of convergence √ d/n for the Gibbs estimator under the absolute loss were given in a previous work [7], where n is t
Externí odkaz:
https://doaj.org/article/3f7aac27fe174c3bb701dd7ff6d248fb
This paper introduces a new principled approach for off-policy learning in contextual bandits. Unlike previous work, our approach does not derive learning principles from intractable or loose bounds. We analyse the problem through the PAC-Bayesian le
Externí odkaz:
http://arxiv.org/abs/2210.13132
We study the deviation inequality for a sum of high-dimensional random matrices and operators with dependence and arbitrary heavy tails. There is an increase in the importance of the problem of estimating high-dimensional matrices, and dependence and
Externí odkaz:
http://arxiv.org/abs/2210.09756