no code implementations • 23 Feb 2023 • Charles Riou, Pierre Alquier, Badr-Eddine Chérief-Abdellatif
Bernstein's condition is a key assumption that guarantees fast rates in machine learning.
no code implementations • 24 Oct 2022 • Otmane Sakhi, Pierre Alquier, Nicolas Chopin
This paper introduces a new principled approach for off-policy learning in contextual bandits.
no code implementations • 13 Oct 2022 • Geoffrey Wolfer, Pierre Alquier
An important feature of kernel mean embeddings (KME) is that the rate of convergence of the empirical KME to the true distribution KME can be bounded independently of the dimension of the space, properties of the distribution and smoothness features of the kernel.
no code implementations • 21 Oct 2021 • Pierre Alquier
Aggregated predictors are obtained by making a set of basic predictors vote according to some weights, that is, to some probability distribution.
no code implementations • 17 Feb 2021 • Xiequan Fan, Pierre Alquier, Paul Doukhan
We introduce a class of Markov chains, that contains the model of stochastic approximation by averaging and non-averaging.
no code implementations • 4 Feb 2021 • Dimitri Meunier, Pierre Alquier
We consider an online meta-learning scenario, and we propose a meta-strategy to learn these parameters from past tasks.
2 code implementations • 7 Oct 2020 • Thang Doan, Mehdi Bennani, Bogdan Mazoure, Guillaume Rabusseau, Pierre Alquier
Continual learning (CL) is a setting in which an agent has to learn from an incoming stream of data during its entire lifetime.
no code implementations • 7 Sep 2020 • Pierre Alquier
We tackle the problem of online optimization with a general, possibly unbounded, loss function.
no code implementations • 12 Dec 2019 • Badr-Eddine Chérief-Abdellatif, Pierre Alquier
Many works in statistics aim at designing a universal estimation procedure, that is, an estimator that would converge to the best approximation of the (unknown) data generating distribution in a model, without any assumption on this distribution.
no code implementations • pproximateinference AABI Symposium 2019 • Badr-Eddine Chérief-Abdellatif, Pierre Alquier
In some misspecified settings, the posterior distribution in Bayesian statistics may lead to inconsistent estimates.
no code implementations • 2 May 2019 • Pierre Alquier, Karine Bertin, Paul Doukhan, Rémy Garnier
We propose a vector auto-regressive (VAR) model with a low-rank constraint on the transition matrix.
no code implementations • 8 Apr 2019 • Badr-Eddine Chérief-Abdellatif, Pierre Alquier, Mohammad Emtiyaz Khan
Our work in this paper presents theoretical justifications in favor of online algorithms relying on approximate Bayesian methods.
no code implementations • 27 Aug 2018 • Pierre Alquier, Paul Doukhan, Xiequan Fan
In this paper, we extend the basic tools of Dedecker and Fan (2015) to nonstationary Markov chains.
no code implementations • 28 Jun 2017 • Pierre Alquier, James Ridgway
While Bayesian methods are extremely popular in statistics and machine learning, their application to massive datasets is often challenging, when possible at all.
no code implementations • 27 Oct 2016 • Pierre Alquier, The Tien Mai, Massimiliano Pontil
We consider the problem of transfer learning in an online setting.
no code implementations • 23 Oct 2016 • Pierre Alquier, Benjamin Guedj
In these bounds the Kullack-Leibler divergence is replaced with a general version of Csisz\'ar's $f$-divergence.
no code implementations • 14 Apr 2016 • Vincent Cottet, Pierre Alquier
We also study the performance of this variational approximation through PAC-Bayesian learning bounds.
no code implementations • 6 Jan 2016 • Pierre Alquier, Benjamin Guedj
The aim of this paper is to provide some theoretical understanding of quasi-Bayesian aggregation methods non-negative matrix factorization.
no code implementations • 12 Jun 2015 • Pierre Alquier, James Ridgway, Nicolas Chopin
We consider instead variational approximations of the Gibbs posterior, which are fast to compute.
no code implementations • NeurIPS 2014 • James Ridgway, Pierre Alquier, Nicolas Chopin, Feng Liang
We also extend our method to a class of non-linear score functions, essentially leading to a nonparametric procedure, by considering a Gaussian process prior.
no code implementations • 5 Jun 2014 • Pierre Alquier, Vincent Cottet, Nicolas Chopin, Judith Rousseau
While the behaviour of algorithms based on nuclear norm minimization is now well understood, an as yet unexplored avenue of research is the behaviour of Bayesian algorithms in this context.
no code implementations • 17 Jun 2013 • Pierre Alquier
The problem of low-rank matrix estimation recently received a lot of attention due to challenging applications.