Search Results for author: Pierre Alquier

Found 19 papers, 1 papers with code

User-friendly introduction to PAC-Bayes bounds

no code implementations21 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.

Learning Theory

Deviation inequalities for stochastic approximation by averaging

no code implementations17 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.

Meta-strategy for Learning Tuning Parameters with Guarantees

no code implementations4 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.


A Theoretical Analysis of Catastrophic Forgetting through the NTK Overlap Matrix

1 code implementation7 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.

Continual Learning

Non-exponentially weighted aggregation: regret bounds for unbounded loss functions

no code implementations7 Sep 2020 Pierre Alquier

We tackle the problem of online optimization with a general, possibly unbounded, loss function.

Finite sample properties of parametric MMD estimation: robustness to misspecification and dependence

no code implementations12 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.

MMD-Bayes: Robust Bayesian Estimation via Maximum Mean Discrepancy

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.

High dimensional VAR with low rank transition

no code implementations2 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.

A Generalization Bound for Online Variational Inference

no code implementations8 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.

Bayesian Inference Generalization Bounds +1

Exponential inequalities for nonstationary Markov Chains

no code implementations27 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.

Learning Theory Time Series

Concentration of tempered posteriors and of their variational approximations

no code implementations28 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.

Collaborative Filtering Matrix Completion

Simpler PAC-Bayesian Bounds for Hostile Data

no code implementations23 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.

An Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization

no code implementations6 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.

PAC-Bayesian AUC classification and scoring

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.

Classification Feature Selection +1

Bayesian matrix completion: prior specification

no code implementations5 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.

Matrix Completion Recommendation Systems

Bayesian methods for low-rank matrix estimation: short survey and theoretical study

no code implementations17 Jun 2013 Pierre Alquier

The problem of low-rank matrix estimation recently received a lot of attention due to challenging applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.