Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Entropy Year : 2021

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

Abstract

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.
Fichier principal
Vignette du fichier
main-pcurves.pdf (1.71 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01796011 , version 1 (18-05-2018)
hal-01796011 , version 2 (08-05-2019)

Identifiers

Cite

Benjamin Guedj, Le Li. Sequential Learning of Principal Curves: Summarizing Data Streams on the Fly. Entropy, 2021, ⟨10.3390/e23111534⟩. ⟨hal-01796011v2⟩
111 View
172 Download

Altmetric

Share

Gmail Facebook X LinkedIn More