Title :

Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly

Author(s) :

Guedj, Benjamin [Auteur]
MOdel for Data Analysis and Learning [MODAL]
Inria-CWI [Inria-CWI]
University College of London [London] [UCL]
Department of Computer science [University College of London] [UCL-CS]
Li, Le [Auteur]
Laboratoire Angevin de Recherche en Mathématiques [LAREMA]

Journal title :

Entropy

Publisher :

MDPI

Publication date :

2021

ISSN :

1099-4300

English keyword(s) :

sequential learning
principal curves
data streams
regret bounds
greedy algorithm
sleeping experts

HAL domain(s) :

Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Apprentissage [cs.LG]
Mathématiques [math]/Statistiques [math.ST]

English abstract : [en]

When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. Principal curves act as a nonlinear generalization of PCA and the present ...
Show more >When confronted with massive data streams, summarizing data with dimension reduction methods such as PCA raises theoretical and algorithmic pitfalls. Principal curves act as a nonlinear generalization of PCA and the present paper proposes a novel algorithm to automatically and sequentially learn principal curves from data streams. We show that our procedure is supported by regret bounds with optimal sublinear remainder terms. A greedy local search implementation (called \texttt{slpc}, for Sequential Learning Principal Curves) that incorporates both sleeping experts and multi-armed bandit ingredients is presented, along with its regret computation and performance on synthetic and real-life data.Show less >

Language :

Anglais

Popular science :

Non

ANR Project :

Une Perspective PAC-Bayésienne de l'Apprentissage de Représentations
Apprentissage PAC-bayésien agnostique
Centre de Mathématiques Henri Lebesgue : fondements, interactions, applications et Formation

Collections :

• Laboratoire Paul Painlevé - UMR 8524

Source :

Harvested from HAL