Title :

A Quasi-Bayesian Perspective to Online Clustering

Author(s) :

Li, Le [Auteur]
Laboratoire Angevin de Recherche en Mathématiques [LAREMA]
Guedj, Benjamin [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Loustau, Sébastien [Auteur]
LumenAI

Journal title :

Electronic Journal of Statistics

Publisher :

Shaker Heights, OH : Institute of Mathematical Statistics

Publication date :

2018

ISSN :

1935-7524

English keyword(s) :

Reversible Jump Markov Chain Monte Carlo
Minimax regret bounds
Quasi-Bayesian learning
Online clustering

HAL domain(s) :

Statistiques [stat]/Machine Learning [stat.ML]
Statistiques [stat]/Théorie [stat.TH]
Mathématiques [math]/Statistiques [math.ST]

English abstract : [en]

When faced with high frequency streams of data, clustering raises theoretical and algorithmic pitfalls. We introduce a new and adaptive online clustering algorithm relying on a quasi-Bayesian approach, with a dynamic (i.e., ...
Show more >When faced with high frequency streams of data, clustering raises theoretical and algorithmic pitfalls. We introduce a new and adaptive online clustering algorithm relying on a quasi-Bayesian approach, with a dynamic (i.e., time-dependent) estimation of the (unknown and changing) number of clusters. We prove that our approach is supported by minimax regret bounds. We also provide an RJMCMC-flavored implementation (called PACBO, see https://cran.r-project.org/web/packages/PACBO/index.html) for which we give a convergence guarantee. Finally, numerical experiments illustrate the potential of our procedure.Show less >

Language :

Anglais

Popular science :

Non

ANR Project :

Centre de Mathématiques Henri Lebesgue : fondements, interactions, applications et Formation

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL